A survey of transfer learning

Karl R. Weiss, Taghi M. Khoshgoftaar, Dingding Wang · Journal Of Big Data · 2016 · machine-learning · 10.1186/s40537-016-0043-6 · record weiss2016-a-survey-of-transfer-learning
tag layer · index · concepts · authors · עברית

Where this record's text came from. 2026-08-20 and 2026-08-26 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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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 An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason.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
transfer learning 6 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 27 concept tags on this paper, all 27 are grounded in a quoted sentence. 7 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

transfer learning domain adaptation negative transfer positive transfer feature space domain D task T label space predictive function supervised transfer learning semi-supervised transfer learning inductive transfer learning transductive transfer learning unsupervised transfer learning terminology inconsistencies pseudo labels marginal distribution conditional distribution source domain target domain context feature bias Transfer Categories asymmetric feature transformation symmetric feature transformation feature augmentation method informed supervised transfer learning WHY TRANSFER LEARNING EXISTS AT ALL: ordinary machine learning assumes train and test come from one domain with one distribution, and the method is what you do when that assumption is false and the target data is expensive to collect NEGATIVE TRANSFER IS DEFINED BY COMPARISON, NOT BY DAMAGE: a learner trained on the target alone is compared against one trained with the source added, and transfer is negative when the plain learner wins PSEUDO LABELS CORRECT A DISTRIBUTION USING GUESSES AT THE THING BEING CORRECTED FOR: with no labeled target data, labels are estimated and then used to fix the conditional distribution - which the paper itself calls problematic review

Method, as described: a survey organised by whether the source and target share a feature space, and by what is transferred

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
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
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

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/10.1186/s40537-016-0043-6. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_type 1 · concept_edges 5 · concepts 27 · content_tags 5 · contribution 1 · limitations 6 · mechanisms 10 · method 1 · object_of_study 1 · phenomenon 1 · research_question 1 · senses 8

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; none of 5 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	the transfer learning literature - solutions, applications, and the terminology used to describe them 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	what to do when the assumption that training and test data share a domain and a distribution does not hold 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 formal definition of transfer learning and an explicit account of where the literature's own terms conflict 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	critique 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	improving a target learner using information from a different but related source domain 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: WHY TRANSFER LEARNING EXISTS AT ALL: ordinary machine learning assumes train and test come from one domain with one distribution, and the method is what you do when that assumption is false and the target data is expensive to collect	`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: NEGATIVE TRANSFER IS DEFINED BY COMPARISON, NOT BY DAMAGE: a learner trained on the target alone is compared against one trained with the source added, and transfer is negative when the plain learner wins	`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: PSEUDO LABELS CORRECT A DISTRIBUTION USING GUESSES AT THE THING BEING CORRECTED FOR: with no labeled target data, labels are estimated and then used to fix the conditional distribution - which the paper itself calls problematic	`mechanisms[2]`	0.95	the tagger's words
mechanisms	instance transfer reweights source examples to correct MARGINAL distribution differences, and works best precisely when the CONDITIONAL distribution is already the same Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[3]`	0.95	the tagger's words
mechanisms	the two feature approaches differ in direction: one bends the source onto the target, the other maps both into a shared latent space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[4]`	0.95	the tagger's words
mechanisms	parameter transfer shares model parameters or combines multiple reweighted source learners into an ensemble for the target Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[5]`	0.9	the tagger's words
mechanisms	source classifiers are weighted by how close their conditional distribution is to the target, summed, and used to manufacture pseudo labels for unlabelled target data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[6]`	0.95	the tagger's words
mechanisms	THE FIELD IS DECLARED TERMINOLOGICALLY INCONSISTENT AND THE PAPER SAYS SO IN ITS OWN VOICE: `Quotation withheld` A survey opening by stipulating the vocabulary because the literature has none. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[7]`	0.95	the tagger's words
mechanisms	THE SAME CONFIGURATION, RENAMED IN THE NEXT SENTENCE: `Quotation withheld.` The sentence immediately before it - quoted separately on this record - gives that exact configuration to Daume and Chattopadhyay as SUPERVISED. The full four-scheme enumeration spans several sentences with a journal running header splicing one of them, so it is carried across four tags on this record rather than asserted from one span. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[8]`	0.95	the tagger's words
mechanisms	AND THE PAPER'S REPAIR IS TO REFUSE THE VOCABULARY ALTOGETHER: `Quotation withheld.` It does not pick a winner and does not coin a fifth term - it describes the configuration and drops the names. THE SAME MOVE CONSORT MADE IN 2010, replacing `intention to treat` with `a more explicit request for information` (schulz2010). Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`mechanisms[9]`	0.95	the tagger's words
limitations	THE LITERATURE'S VOCABULARY IS INCONSISTENT AND THE PAPER SAYS SO: transfer learning and domain adaptation are used for similar processes, and the supervised / semi-supervised / unsupervised labels mean different things to different authors 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	Some surveyed solutions are tied to their application and are stated not to generalise to others 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	Correcting the conditional distribution rests on pseudo labels, which the paper names as problematic because the correction uses estimates of the very labels it lacks 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	No single repository exists for the surveyed solutions, so the software behind the literature is scattered - the paper asks for one 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
limitations	heterogeneous solutions mostly assume the domain distributions are the SAME, and need further adaptation steps when they are not Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[4]`	0.95	the tagger's words
limitations	transferring on a defined relationship between domains is named as the least used of the four categories Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`limitations[5]`	0.9	the tagger's words
concepts	transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transfer learning	`concepts[0]`	0.95	the paper's words
concepts	domain adaptation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: domain adaptation	`concepts[1]`	0.95	the paper's words
concepts	negative transfer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: negative transfer	`concepts[2]`	0.95	the paper's words
concepts	positive transfer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: positive transfer	`concepts[3]`	0.95	the paper's words
concepts	feature space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: feature space	`concepts[4]`	0.95	the paper's words
concepts	domain D Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: domain D	`concepts[5]`	0.95	the paper's words
concepts	task T Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: task T	`concepts[6]`	0.85	the paper's words
concepts	label space Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: label space	`concepts[7]`	0.85	the paper's words
concepts	predictive function Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: predictive function	`concepts[8]`	0.85	the paper's words
concepts	supervised transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: supervised transfer learning	`concepts[9]`	0.95	the paper's words
concepts	semi-supervised transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: semi-supervised transfer learning	`concepts[10]`	0.95	the paper's words
concepts	inductive transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: inductive transfer learning	`concepts[11]`	0.95	the paper's words
concepts	transductive transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transductive transfer learning	`concepts[12]`	0.95	the paper's words
concepts	unsupervised transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: unsupervised transfer learning	`concepts[13]`	0.95	the paper's words
concepts	terminology inconsistencies Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: terminology inconsistencies	`concepts[14]`	0.95	the paper's words
concepts	pseudo labels Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pseudo labels	`concepts[15]`	0.95	the paper's words
concepts	marginal distribution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: marginal distribution	`concepts[16]`	0.95	the paper's words
concepts	conditional distribution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: conditional distribution	`concepts[17]`	0.95	the paper's words
concepts	source domain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: source domain	`concepts[18]`	0.95	the paper's words
concepts	target domain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: target domain	`concepts[19]`	0.95	the paper's words
concepts	context feature bias Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: context feature bias	`concepts[20]`	0.95	the paper's words
concepts	Transfer Categories Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Transfer Categories	`concepts[21]`	0.95	the paper's words
concepts	asymmetric feature transformation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: asymmetric feature transformation	`concepts[22]`	0.95	the paper's words
concepts	symmetric feature transformation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: symmetric feature transformation	`concepts[23]`	0.95	the paper's words
concepts	feature augmentation method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: feature augmentation method	`concepts[24]`	0.9	the paper's words
concepts	informed supervised transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: informed supervised transfer learning	`concepts[25]`	0.95	the paper's words
concepts	transductive transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transductive transfer learning	`concepts[26]`	0.95	the paper's words
senses	supervised transfer learning - DAUME AND CHATTOPADHYAY'S SENSE: abundant labeled source data and LIMITED labeled target data 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	semi-supervised transfer learning - DAUME AND CHATTOPADHYAY'S SENSE: abundant labeled source and NO labeled target. Gong and Blitzer use this same phrase for what Daume calls SUPERVISED - the two labels are swapped between literatures 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	unsupervised transfer learning - PAN'S SENSE: NO labeled source and NO labeled target, where the same phrase elsewhere in the literature means abundant labeled source and no labeled target. THREE GROUPS, ONE VOCABULARY, THREE MAPPINGS 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	transfer learning - the paper's response to its own finding: it refuses the contested labels entirely and states the data conditions each time instead of naming them 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	`supervised transfer learning` - DAUME AND CHATTOPADHYAY'S SENSE: `abundant labeled source data and LIMITED labeled target data`. Gong and Blitzer give that same configuration to SEMI-SUPERVISED, and Cook and Feuz call it INFORMED SUPERVISED. 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	`semi-supervised transfer learning` - GONG AND BLITZER'S SENSE: `abundant labeled source data and LIMITED labeled target data`. THAT IS THE CONFIGURATION Daume and Chattopadhyay CALL SUPERVISED - see senses[4] and the `daume` mechanism on this record, which quote their sentence. One name over two configurations and one configuration under two names, in consecutive sentences. 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	`supervised` / `unsupervised` - COOK AND FEUZ MOVE THE AXIS: the pair refers to `the presence or absence of labeled data in the source domain` and a SECOND pair, `informed` / `uninformed`, carries the target. Two orthogonal axes where the other schemes have one. 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	`domain adaptation` - AS STIPULATED HERE, because the field does not agree: `the process of adapting one or more source domains for the means of transferring information to improve the performance of a target learner`, by bringing the source's distribution closer to the target's. 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
concept_edges	domain adaptation —part-of→ transfer learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 0.9 also in: domain adaptation · transfer learning	`concept_edges[0]`		the tagger's words
concept_edges	negative transfer —distinct-from→ positive transfer Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but endpoint by anaphora: 'the definition above' = negative transfer (previous sentences); distinct-from is loose. also in: negative transfer · positive transfer	`concept_edges[1]`		the tagger's words
concept_edges	feature space —part-of→ domain D Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: feature space · domain D	`concept_edges[2]`		the tagger's words
concept_edges	label space —part-of→ task T Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: label space · task T	`concept_edges[3]`		the tagger's words
concept_edges	predictive function —part-of→ task T Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 also in: predictive function · task T	`concept_edges[4]`		the tagger's words
content_tags	in the muscle-fatigue test EVERY transfer learning approach beat the non-transfer baseline, with the two proposed methods ranking first and second Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[0]`	0.95	the tagger's words
content_tags	an often-cited domain adaptation method is reported as requiring only ten lines of Perl - the simplicity is the claim Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[1]`	0.9	the tagger's words
content_tags	Homogeneous transfer learning is directly applicable to big data environments. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.findings[2]`	0.95	the tagger's words
content_tags	the four transfer categories enumerated by what is carried across Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: transfer categories	`content_tags.definitions[0]`	0.95	the tagger's words
content_tags	context feature bias defined by its consequence - it makes the conditional distributions differ Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: context feature bias	`content_tags.definitions[1]`	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.