Papers › Transporting Causal Mechanisms for Unsupervised Domain Adaptation

Transporting Causal Mechanisms for Unsupervised Domain Adaptation

23 Jul 2021ICCV 2021 10arXiv:2107.11055archive 2025-07-28

Zhongqi Yue, Qianru Sun, Xian-Sheng Hua, Hanwang Zhang

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the feature will inevitably lose non-discriminative semantics in source domain, which is however discriminative in target domain. We use a causal view -- transportability theory -- to identify that such loss is in fact a confounding effect, which can only be removed by causal intervention. However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap. To this end, we propose a practical solution: Transporting Causal Mechanisms (TCM), to identify the confounder stratum and representations by using the domain-invariant disentangled causal mechanisms, which are discovered in an unsupervised fashion. Our TCM is both theoretically and empirically grounded. Extensive experiments show that TCM achieves state-of-the-art performance on three challenging UDA benchmarks: ImageCLEF-DA, Office-Home, and VisDA-2017. Codes are available in Appendix.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yue-zhongqi/tcm officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 6 ran (2 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
4ran
4unverified

Licence: 10 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yue-zhongqi/tcm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

yue-zhongqi/tcm official repository 10 samples, 6 ran (2 instrument-failed) · 4 unverified
AdversarialLoss dda_model/dda_model.py ran no licence file found · pointer only · bfd1bf2f89a925df · report fixture: returned AdversarialLoss · level recorded 2026-09-22
AdversarialNetwork dda_model/dda_model.py ran no licence file found · pointer only · 4060dcdef9dece76 · report fixture: returned AdversarialNetwork · level recorded 2026-09-22
Entropy in 31 papers
census: 7 implementations from 10 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
dda_model/dda_model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a4fb3d7d83bd280c · report fixture: signature input_:Tensor/2/float · returned Tensor · level recorded 2026-09-22
NMTCritierion dda_model/dda_model.py ran no licence file found · pointer only · eebaad56ac7a9f66 · report fixture: returned NMTCritierion · level recorded 2026-09-22
VAE in 29 papers dda_model/dda_model.py ran no licence file found · pointer only · c365fefa76406516 · report fixture: returned VAE · level recorded 2026-09-22
init_net in 47 papers dda_model/dda_model.py ran · our draft was wrong no licence file found · pointer only · 00412bee7f16f8c4 · report fixture: signature net:callable/0/?, init_type:str/0/str, init_gain:float/0/float, gpu_ids:list/1/empty, parallel:bool/0/bool, init_weight:bool/0/bool · returned SimpleNet · level recorded 2026-09-22
DDAModel dda_model/dda_model.py unverified no licence file found · pointer only · 12766c6671066235 · report
ResNet in 139 papers dda_model/dda_model.py unverified no licence file found · pointer only · 8904685cc0f51333 · report
get_alignment_loss dda_model/dda_model.py unverified no licence file found · pointer only · a09ed0d9ca4440f9 · report
init_weights in 109 papers dda_model/dda_model.py unverified no licence file found · pointer only · d3473ef03b54a28d · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Transporting Causal Mechanisms (TCM) (graph method: Transporting Causal Mechanisms (TCM)). 12 bricks; individually on a fixture: 7 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. DDAModel entry · level 0 · unverified · 12766c6671066235
  2. AdversarialNetwork helper · level 1 · ran · 4060dcdef9dece76
  3. NMTCritierion loss · level 1 · ran · eebaad56ac7a9f66
  4. ResNet helper · level 0 · unverified · 8904685cc0f51333
  5. VAE helper · level 1 · ran · c365fefa76406516
  6. calc_coeff helper · level 0 · unverified · e352afa5762c5a6b
  7. get_alignment_loss loss · level 0 · unverified · a09ed0d9ca4440f9
  8. init_net helper · level 1 · ran · our draft was wrong · 00412bee7f16f8c4
  9. grl_hook helper · level 1 · ran · our draft was wrong · 9768efb52f591b55
  10. init_weights helper · level 0 · unverified · d3473ef03b54a28d
  11. AdversarialLoss loss · level 1 · ran · bfd1bf2f89a925df
  12. Entropy helper · level 1 · ran · our draft was wrong · a4fb3d7d83bd280c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2107.11055") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections