The future of digital health with federated learning

Nicola Rieke, Jonny Hancox, Wenqi Li, Fausto Milletarì, Holger R. Roth, Shadi Albarqouni, Spyridon Bakas, Mathieu N. Galtier, Bennett A. Landman, Klaus Maier-Hein, Sébastien Ourselin, Micah Sheller, Ronald M. Summers, Andrew Trask, Daguang Xu, Maximilian Baust, M. Jorge Cardoso · npj Digital Medicine · 2020 · machine-learning · 10.1038/s41746-020-00323-1 · record rieke2020-the-future-of-digital-health-with
tag layer · index · concepts · authors · עברית

Where this record's text came from. 2026-08-20 and 2026-08-28 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

This record’s own method is review, and the tags below follow from that. A review’s findings, quantities and statistics are things stated IN this paper, and some of them report results obtained elsewhere. No tag on this page names a different author. Measured across every review in this corpus, 81% of a review’s tags carry no citation at all — most of them are the review speaking. The corpus does not adjudicate the rest: read an unmarked tag as a claim this paper makes, not necessarily one it made first.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
privacy 3 fields · compensation 2 fields

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 110 concept tags on this paper, all 110 are grounded in a quoted sentence. 99 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

Federated learning data governance consensus model anonymisation reidentification privacy precision medicine license restrictions egress business value firewalls Data-driven machine learning (ML) accurate and robust statistical models data silos privacy concerns without access to sufficient data full potential transition from research to clinical practice Centralised Data Lake FL aggregation server federation of training nodes global model partially trained models central server FL peer to peer Centralised training local, independent training ML from non-co-located data data controller governance processes privacy policies data access validation phase large-scale, ininstitutional validation rare diseases high-dimensional, storage-intense medical data centralised pool growing global data set data storage requirements FL topologies Centralised Decentralised Hierarchical FL compute plans Sequential training/cyclic transfer learning memorise information differential privacy learning from encrypted data volume-based fee-for-service-based value-based healthcare focused treatment accuracy and robustness of healthcare AI costs patient outcomes FL learning paradigm multiple parties global loss function weighted combination of K local losses private data data heterogeneity inhomogeneous data distribution independently and identically distributed (IID) data FedAvg FedProx part-data-sharing strategy FL with domainadaptation global optimal solution optimal for an individual local participant model training optimality Privacy-preserving techniques for FL levels of protection accuracy of the final model future techniques ancillary data low-risk Non-trusted security strategies advanced encryption of model submissions secure authentication of all parties traceability of actions verification systems execution integrity model confidentiality protections against adversarial attacks traditional training training process is exposed to multiple parties risk of leakage via reverseengineering multiparty computations training configurations hyperparameter tuning contribution from each participant computational resources consumed quality of the data used for local training compensation revenue model secure intra-node viewing facility explainability and interpretability of the global model redundant nodes secure encryption methods data leakage node schedulers “honest broker” system trusted third party peer-topeer system gatekeeper function trustlessbased architecture secure protocol computational overheads MOVE THE MODEL, NOT THE DATA: training happens locally inside each institution and only model characteristics leave the firewall, so the consensus model is built without the patient records ever being pooled WHY ANONYMISATION CANNOT BE THE ANSWER: identity survives the removal of the obvious fields - a face is reconstructable from a CT scan, and a handful of record elements permits reidentification DATA IS WITHHELD FOR COMMERCIAL REASONS AS WELL AS LEGAL ONES: curating a high-quality set costs time and money, which gives it business value and makes sharing less likely - a motive no privacy technology addresses review

Method, as described: a perspective paper: no new experiment, performance claims cited from prior work

Legend

claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
contribution	`contribution`	what the paper claims to add
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
object of study	`object_of_study`	what the paper is about — the thing it investigates
phenomenon	`phenomenon`	the effect or regularity under study
research question	`research_question`	the question the paper sets itself
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
unrecordable relation	`unhoused_relations`	a relation the paper asserts that this vocabulary cannot express, with the reason

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.1038/s41746-020-00323-1. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_type 1 · concept_edges 11 · concepts 110 · contribution 1 · limitations 4 · mechanisms 3 · method 1 · object_of_study 1 · phenomenon 1 · research_question 1 · senses 13 · unhoused_relations 5

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; 10 of 11 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

This record holds no relations between claims or controls. A layer is empty when the tagger recorded nothing in it — which is not the same as the paper having nothing to record.

facet	tag	field	conf.	whose words
object_of_study	federated learning as an answer to data governance and privacy constraints in healthcare machine learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`object_of_study`		the paper's words
research_question	how to train on medical data that cannot be centralised Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`research_question`		the paper's words
contribution	a consensus perspective on what FL offers digital health and what it still requires Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`contribution`		the paper's words
claim_type	prediction Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	medical data sitting in silos that machine learning cannot reach Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	review Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: review	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: MOVE THE MODEL, NOT THE DATA: training happens locally inside each institution and only model characteristics leave the firewall, so the consensus model is built without the patient records ever being pooled	`mechanisms[0]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: WHY ANONYMISATION CANNOT BE THE ANSWER: identity survives the removal of the obvious fields - a face is reconstructable from a CT scan, and a handful of record elements permits reidentification	`mechanisms[1]`	0.95	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: DATA IS WITHHELD FOR COMMERCIAL REASONS AS WELL AS LEGAL ONES: curating a high-quality set costs time and money, which gives it business value and makes sharing less likely - a motive no privacy technology addresses	`mechanisms[2]`	0.95	the tagger's words
limitations	FL is stated to still require rigorous technical consideration to avoid compromising safety or patient privacy - the paradigm is offered as promising rather than solved Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[0]`	0.95	the tagger's words
limitations	The authors say plainly that not all technical questions have been answered and expect FL to remain an open research area for a decade Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[1]`	0.95	the tagger's words
limitations	The performance claim is attributed to other work rather than demonstrated here - this is a perspective paper citing comparisons, not running them Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[2]`	0.95	the tagger's words
limitations	Public medical data carries varying license restrictions that sometimes limit its exploitation, which bounds what any centralised alternative could have used anyway Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[3]`	0.95	the tagger's words
concepts	Federated learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Federated learning	`concepts[0]`	0.95	the paper's words
concepts	data governance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data governance	`concepts[1]`	0.95	the paper's words
concepts	consensus model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: consensus model	`concepts[2]`	0.95	the paper's words
concepts	anonymisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: anonymisation	`concepts[3]`	0.95	the paper's words
concepts	reidentification Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: reidentification	`concepts[4]`	0.95	the paper's words
concepts	privacy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: privacy	`concepts[5]`	0.95	the paper's words
concepts	precision medicine Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: precision medicine	`concepts[6]`	0.85	the paper's words
concepts	license restrictions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: license restrictions	`concepts[7]`	0.95	the paper's words
concepts	egress Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: egress	`concepts[8]`	0.95	the paper's words
concepts	business value Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: business value	`concepts[9]`	0.95	the paper's words
concepts	firewalls Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: firewalls	`concepts[10]`	0.95	the paper's words
concepts	Data-driven machine learning (ML) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Data-driven machine learning (ML)	`concepts[11]`	0.95	the paper's words
concepts	accurate and robust statistical models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: accurate and robust statistical models	`concepts[12]`	0.95	the paper's words
concepts	data silos Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data silos	`concepts[13]`	0.95	the paper's words
concepts	privacy concerns Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: privacy concerns	`concepts[14]`	0.95	the paper's words
concepts	without access to sufficient data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: without access to sufficient data	`concepts[15]`	0.95	the paper's words
concepts	full potential Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: full potential	`concepts[16]`	0.95	the paper's words
concepts	transition from research to clinical practice Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transition from research to clinical practice	`concepts[17]`	0.95	the paper's words
concepts	Centralised Data Lake Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Centralised Data Lake	`concepts[18]`	0.95	the paper's words
concepts	FL aggregation server Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL aggregation server	`concepts[19]`	0.95	the paper's words
concepts	federation of training nodes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: federation of training nodes	`concepts[20]`	0.95	the paper's words
concepts	global model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: global model	`concepts[21]`	0.95	the paper's words
concepts	partially trained models Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: partially trained models	`concepts[22]`	0.95	the paper's words
concepts	central server Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: central server	`concepts[23]`	0.95	the paper's words
concepts	FL peer to peer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL peer to peer	`concepts[24]`	0.95	the paper's words
concepts	Centralised training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Centralised training	`concepts[25]`	0.95	the paper's words
concepts	local, independent training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: local, independent training	`concepts[26]`	0.95	the paper's words
concepts	ML from non-co-located data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ML from non-co-located data	`concepts[27]`	0.95	the paper's words
concepts	data controller Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data controller	`concepts[28]`	0.95	the paper's words
concepts	governance processes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: governance processes	`concepts[29]`	0.95	the paper's words
concepts	privacy policies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: privacy policies	`concepts[30]`	0.95	the paper's words
concepts	data access Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data access	`concepts[31]`	0.95	the paper's words
concepts	validation phase Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: validation phase	`concepts[32]`	0.95	the paper's words
concepts	large-scale, ininstitutional validation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: large-scale, ininstitutional validation	`concepts[33]`	0.95	the paper's words
concepts	rare diseases Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: rare diseases	`concepts[34]`	0.95	the paper's words
concepts	high-dimensional, storage-intense medical data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: high-dimensional, storage-intense medical data	`concepts[35]`	0.95	the paper's words
concepts	centralised pool Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: centralised pool	`concepts[36]`	0.95	the paper's words
concepts	growing global data set Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: growing global data set	`concepts[37]`	0.95	the paper's words
concepts	data storage requirements Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data storage requirements	`concepts[38]`	0.95	the paper's words
concepts	FL topologies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL topologies	`concepts[39]`	0.95	the paper's words
concepts	Centralised Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Centralised	`concepts[40]`	0.95	the paper's words
concepts	Decentralised Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Decentralised	`concepts[41]`	0.95	the paper's words
concepts	Hierarchical Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Hierarchical	`concepts[42]`	0.95	the paper's words
concepts	FL compute plans Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL compute plans	`concepts[43]`	0.95	the paper's words
concepts	Sequential training/cyclic transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Sequential training/cyclic transfer learning	`concepts[44]`	0.95	the paper's words
concepts	memorise information Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: THE QUOTE CONTINUES A SENTENCE THAT THIS COPY CUTS IN TWO - a figure caption (the FL compute plans panels) stands between it and the words it follows, which are not adjacent to it in the extraction. also in: memorise information	`concepts[45]`	0.95	the paper's words
concepts	differential privacy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: THE QUOTE CONTINUES A SENTENCE THAT THIS COPY CUTS IN TWO - a figure caption (the FL compute plans panels) stands between it and the words it follows, which are not adjacent to it in the extraction. also in: differential privacy	`concepts[46]`	0.95	the paper's words
concepts	learning from encrypted data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: THE QUOTE CONTINUES A SENTENCE THAT THIS COPY CUTS IN TWO - a figure caption (the FL compute plans panels) stands between it and the words it follows, which are not adjacent to it in the extraction. also in: learning from encrypted data	`concepts[47]`	0.95	the paper's words
concepts	volume-based Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: volume-based	`concepts[48]`	0.95	the paper's words
concepts	fee-for-service-based Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fee-for-service-based	`concepts[49]`	0.95	the paper's words
concepts	value-based healthcare Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: value-based healthcare	`concepts[50]`	0.95	the paper's words
concepts	focused treatment Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: focused treatment	`concepts[51]`	0.95	the paper's words
concepts	accuracy and robustness of healthcare AI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: accuracy and robustness of healthcare AI	`concepts[52]`	0.95	the paper's words
concepts	costs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: costs	`concepts[53]`	0.95	the paper's words
concepts	patient outcomes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: patient outcomes	`concepts[54]`	0.95	the paper's words
concepts	FL Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL	`concepts[55]`	0.95	the paper's words
concepts	learning paradigm Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learning paradigm	`concepts[56]`	0.95	the paper's words
concepts	multiple parties Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: multiple parties	`concepts[57]`	0.95	the paper's words
concepts	global loss function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: global loss function	`concepts[58]`	0.95	the paper's words
concepts	weighted combination of K local losses Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: weighted combination of K local losses	`concepts[59]`	0.95	the paper's words
concepts	private data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: private data	`concepts[60]`	0.95	the paper's words
concepts	data heterogeneity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data heterogeneity	`concepts[61]`	0.95	the paper's words
concepts	inhomogeneous data distribution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inhomogeneous data distribution	`concepts[62]`	0.95	the paper's words
concepts	independently and identically distributed (IID) data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: independently and identically distributed (IID) data	`concepts[63]`	0.95	the paper's words
concepts	FedAvg Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FedAvg	`concepts[64]`	0.95	the paper's words
concepts	FedProx Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FedProx	`concepts[65]`	0.95	the paper's words
concepts	part-data-sharing strategy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: part-data-sharing strategy	`concepts[66]`	0.95	the paper's words
concepts	FL with domainadaptation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: FL with domainadaptation	`concepts[67]`	0.95	the paper's words
concepts	global optimal solution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: global optimal solution	`concepts[68]`	0.95	the paper's words
concepts	optimal for an individual local participant Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: optimal for an individual local participant	`concepts[69]`	0.95	the paper's words
concepts	model training optimality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: model training optimality	`concepts[70]`	0.95	the paper's words
concepts	Privacy-preserving techniques for FL Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Privacy-preserving techniques for FL	`concepts[71]`	0.95	the paper's words
concepts	levels of protection Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: levels of protection	`concepts[72]`	0.95	the paper's words
concepts	accuracy of the final model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: accuracy of the final model	`concepts[73]`	0.95	the paper's words
concepts	future techniques Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: future techniques	`concepts[74]`	0.95	the paper's words
concepts	ancillary data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ancillary data	`concepts[75]`	0.95	the paper's words
concepts	low-risk Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: low-risk	`concepts[76]`	0.95	the paper's words
concepts	Non-trusted Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Non-trusted	`concepts[77]`	0.95	the paper's words
concepts	security strategies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: security strategies	`concepts[78]`	0.95	the paper's words
concepts	advanced encryption of model submissions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: advanced encryption of model submissions	`concepts[79]`	0.95	the paper's words
concepts	secure authentication of all parties Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: secure authentication of all parties	`concepts[80]`	0.95	the paper's words
concepts	traceability of actions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: traceability of actions	`concepts[81]`	0.95	the paper's words
concepts	verification systems Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: verification systems	`concepts[82]`	0.95	the paper's words
concepts	execution integrity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: execution integrity	`concepts[83]`	0.95	the paper's words
concepts	model confidentiality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: model confidentiality	`concepts[84]`	0.95	the paper's words
concepts	protections against adversarial attacks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: protections against adversarial attacks	`concepts[85]`	0.95	the paper's words
concepts	traditional training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: traditional training	`concepts[86]`	0.95	the paper's words
concepts	training process is exposed to multiple parties Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: training process is exposed to multiple parties	`concepts[87]`	0.95	the paper's words
concepts	risk of leakage via reverseengineering Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: risk of leakage via reverseengineering	`concepts[88]`	0.95	the paper's words
concepts	multiparty computations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: multiparty computations	`concepts[89]`	0.95	the paper's words
concepts	training configurations Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: training configurations	`concepts[90]`	0.95	the paper's words
concepts	hyperparameter tuning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: hyperparameter tuning	`concepts[91]`	0.95	the paper's words
concepts	contribution from each participant Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: contribution from each participant	`concepts[92]`	0.95	the paper's words
concepts	computational resources consumed Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: computational resources consumed	`concepts[93]`	0.95	the paper's words
concepts	quality of the data used for local training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: quality of the data used for local training	`concepts[94]`	0.95	the paper's words
concepts	compensation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: compensation	`concepts[95]`	0.95	the paper's words
concepts	revenue model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: revenue model	`concepts[96]`	0.95	the paper's words
concepts	secure intra-node viewing facility Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: secure intra-node viewing facility	`concepts[97]`	0.95	the paper's words
concepts	explainability and interpretability of the global model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: explainability and interpretability of the global model	`concepts[98]`	0.95	the paper's words
concepts	redundant nodes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: redundant nodes	`concepts[99]`	0.95	the paper's words
concepts	secure encryption methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: secure encryption methods	`concepts[100]`	0.95	the paper's words
concepts	data leakage Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: data leakage	`concepts[101]`	0.95	the paper's words
concepts	node schedulers Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: node schedulers	`concepts[102]`	0.95	the paper's words
concepts	“honest broker” system Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: “honest broker” system	`concepts[103]`	0.95	the paper's words
concepts	trusted third party Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: trusted third party	`concepts[104]`	0.95	the paper's words
concepts	peer-topeer system Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: peer-topeer system	`concepts[105]`	0.95	the paper's words
concepts	gatekeeper function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: gatekeeper function	`concepts[106]`	0.95	the paper's words
concepts	trustlessbased architecture Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: trustlessbased architecture	`concepts[107]`	0.95	the paper's words
concepts	secure protocol Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: secure protocol	`concepts[108]`	0.95	the paper's words
concepts	computational overheads Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: computational overheads	`concepts[109]`	0.95	the paper's words
unhoused_relations	FL → Federated learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. FL expands to Federated learning. Acronym expansion is absent from the eight edge types.	`unhoused_relations[0]`	0.95	the tagger's words
unhoused_relations	FL → ML from non-co-located data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. FL enables machine learning from non-co-located data. Enablement is absent from the eight edge types and is not safely reducible to causation here.	`unhoused_relations[1]`	0.95	the tagger's words
unhoused_relations	Non-trusted → security strategies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Non-trusted FL collaborations require security strategies. Prerequisite-for is absent from the eight edge types.	`unhoused_relations[2]`	0.95	the tagger's words
unhoused_relations	traceability and accountability processes → execution integrity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Traceability and accountability in non-trusted federations require execution integrity. Prerequisite-for is absent from the eight edge types.	`unhoused_relations[3]`	0.95	the tagger's words
unhoused_relations	“honest broker” system → trusted third party Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. An honest-broker federation is administered through a trusted third party acting as intermediary. Administered-through or mediated-by is absent from the eight edge types.	`unhoused_relations[4]`	0.95	the tagger's words
senses	anonymisation - TREATED HERE AS INSUFFICIENT BY CONSTRUCTION, not as imperfect in practice: removing name and date of birth does not preserve privacy, a face can be reconstructed from a CT scan, and genomic data is as unique as a fingerprint Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	0.95	the tagger's words
senses	Federated learning - collaborative model training without exchanging or centralising the parties' data sets Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	0.95	the tagger's words
senses	Aggregation-server FL - nodes receive a global model, train locally, and return partial models for central aggregation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	0.95	the tagger's words
senses	Peer-to-peer FL - each node exchanges partial models with peers and performs its own aggregation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	0.95	the tagger's words
senses	Centralised training - sites donate data to a shared lake for extraction and independent local training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[4]`	0.95	the tagger's words
senses	FL topology - centralised, decentralised, or hierarchical communication architecture Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[5]`	0.95	the tagger's words
senses	FL compute plan - trajectory followed by a model across participating partners Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[6]`	0.95	the tagger's words
senses	Data heterogeneity - non-IID cross-institutional distributions that challenge federated aggregation and local optimality Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[7]`	0.95	the tagger's words
senses	Privacy-performance trade-off - stronger federated protections may affect final-model accuracy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[8]`	0.95	the tagger's words
senses	Non-trusted federation - collaboration needing encryption, authentication, traceability, verification, integrity, and adversarial defenses Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[9]`	0.95	the tagger's words
senses	Federated information leakage - model changes exposed to multiple parties create reverse-engineering risk even without raw-data sharing Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[10]`	0.95	the tagger's words
senses	Honest-broker administration - trusted intermediary controls the federation and abstracts internal mechanisms from clients Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[11]`	0.95	the tagger's words
senses	Peer-to-peer administration - sites interact directly with no gatekeeper and must synchronise protocol changes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[12]`	0.95	the tagger's words
concept_edges	Federated learning —distinct-from→ anonymisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 0.8 Audit 2026-09-28: DOUBTFUL - read against its span and kept, but the span describes federated learning's privacy aim; distinct-from 'anonymisation' is loose. also in: Federated learning · anonymisation	`concept_edges[0]`		the tagger's words
concept_edges	without access to sufficient data —causes→ transition from research to clinical practice Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: eliminates · the relation itself is separately evidenced · strength of the relation: 1 · note: The paper says insufficient access prevents ML from making the research-to-clinic transition. also in: without access to sufficient data · transition from research to clinical practice	`concept_edges[1]`	0.95	the tagger's words
concept_edges	Centralised training —distinct-from→ FL aggregation server Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The figure explicitly presents the difference between federated workflows and the non-FL centralised-data-lake workflow. also in: Centralised training · FL aggregation server	`concept_edges[2]`	0.95	the tagger's words
concept_edges	learning from encrypted data —causes→ privacy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: increases · the relation itself is separately evidenced · strength of the relation: 0.7 · about this quote: THE QUOTE CONTINUES A SENTENCE THAT THIS COPY CUTS IN TWO - a figure caption (the FL compute plans panels) stands between it and the words it follows, which are not adjacent to it in the extraction. · note: The same proposed-mechanism hedge applies, so paper weight is 0.7 while confidence remains 0.95. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says learning from encrypted data HAS BEEN PROPOSED to further enhance privacy; hedged. also in: learning from encrypted data · privacy	`concept_edges[3]`	0.95	the tagger's words
concept_edges	FL —is-a→ learning paradigm Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper directly defines FL as a learning paradigm. also in: FL · learning paradigm	`concept_edges[4]`	0.95	the tagger's words
concept_edges	global optimal solution —distinct-from→ optimal for an individual local participant Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 0.7 · note: The paper says the global optimum may not be locally optimal; weight 0.7 preserves both modal hedges. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says the global optimum MAY not be optimal for a local participant; hedged. also in: global optimal solution · optimal for an individual local participant	`concept_edges[5]`	0.95	the tagger's words
concept_edges	training process is exposed to multiple parties —causes→ risk of leakage via reverseengineering Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: increases · the relation itself is separately evidenced · strength of the relation: 1 · note: The paper directly says multi-party exposure increases reverse-engineering leakage risk. also in: training process is exposed to multiple parties · risk of leakage via reverseengineering	`concept_edges[6]`	0.95	the tagger's words
concept_edges	secure encryption methods —causes→ data leakage Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: reduces · the relation itself is separately evidenced · strength of the relation: 1 · note: Secure encryption is named as an architecture measure to prevent data leakage. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span names designing secure encryption methods to prevent leakage as a CHALLENGE; causes is loose. also in: secure encryption methods · data leakage	`concept_edges[7]`	0.95	the tagger's words
concept_edges	FL —causes→ accuracy and robustness of healthcare AI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: increases · the relation itself is separately evidenced · strength of the relation: 0.7 · note: Weight 0.7 preserves the paper's 'has the potential to increase' wording. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says FL HAS THE POTENTIAL to increase accuracy and robustness; hedged. also in: FL · accuracy and robustness of healthcare AI	`concept_edges[8]`	0.95	the tagger's words
concept_edges	FL —causes→ costs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: reduces · the relation itself is separately evidenced · strength of the relation: 0.7 · note: The projected cost reduction shares the paper's potential-language hedge. Audit 2026-09-28: DOUBTFUL - read against its span and kept, but the span shown is about paradigm shifts in healthcare payment; the cost claim is not visible. also in: FL · costs	`concept_edges[9]`	0.95	the tagger's words
concept_edges	FL —causes→ patient outcomes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: increases · the relation itself is separately evidenced · strength of the relation: 0.7 · note: The projected improvement in patient outcomes is weighted 0.7 for the paper's modal framing. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says FL HAS THE POTENTIAL to improve patient outcomes; hedged. also in: FL · patient outcomes	`concept_edges[10]`	0.95	the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.