Papers › On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation

On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation

1 Feb 2022arXiv:2202.00796archive 2025-07-28

Maohao Shen, Yuheng Bu, Gregory Wornell

Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models. Existing methods for multi-source-free domain adaptation (MSFDA) typically train a target model using pseudo-labeled data produced by the source models, which focus on improving the pseudo-labeling techniques or proposing new training objectives. Instead, we aim to analyze the fundamental limits of MSFDA. In particular, we develop an information-theoretic bound on the generalization error of the resulting target model, which illustrates an inherent bias-variance trade-off. We then provide insights on how to balance this trade-off from three perspectives, including domain aggregation, selective pseudo-labeling, and joint feature alignment, which leads to the design of novel algorithms. Experiments on multiple datasets validate our theoretical analysis and demonstrate the state-of-art performance of the proposed algorithm, especially on some of the most challenging datasets, including Office-Home and DomainNet.

PaperPDFCodeCode Syntology ran

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 11 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 11 ran (6 with no instrument failure; 5 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 11 samples that ran have no recorded date.

maohaos2/MSFDA officialmentioned on GitHubpytorchMITSyntology: 11 samples, 11 ran (5 instrument-failed) · 0 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 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 · honoured contract
5ran · our draft was wrong
4ran

Licence: 6 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from maohaos2/MSFDA. “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”. “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.

maohaos2/MSFDA official repository 11 samples, 11 ran (5 instrument-failed) · 0 unverified
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
loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 94b5622f0aa7add1 · report fixture: signature input_:Tensor/2/float · returned Tensor · level recorded, date not recorded
image_test in 9 papers adapt.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 6e4265b7f707b718 · report fixture: signature resize_size:int/0/int, crop_size:int/0/int, alexnet:bool/0/bool · returned Compose · level recorded 2026-09-22
image_train in 18 papers train_source.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 35c2d572ebd185f5 · report fixture: signature resize_size:int/0/int, crop_size:int/0/int, alexnet:bool/0/bool · returned Compose · level recorded 2026-09-22
image_train in 18 papers adapt.py ran MIT (permissive) · 9c0d2ceeef4fc6b3 · report fixture: signature resize_size:int/0/int, crop_size:int/0/int, alexnet:bool/0/bool · returned Compose · level recorded 2026-09-25
l_loader in 13 papers data_list.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · edd7184ac144c4fa · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22
lr_scheduler in 32 papers train_source.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 0b7ffc9f8b77529c · report fixture: signature optimizer:SGD/0/?, iter_num:int/0/int, max_iter:int/0/int, gamma:int/0/int, power:float/0/float · returned SGD · level recorded, date not recorded
make_dataset in 144 papers data_list.py ran MIT (permissive) · 09ad767f042450a8 · report fixture: signature image_list:list/1/str, labels:list/1/int · returned list · level recorded 2026-09-25
mutual_info_loss loss.py ran fingerprinted MIT (permissive) · b3121e5da47857cc · report fixture: signature prob1:Tensor/2/float · returned Tensor · level recorded 2026-09-25
op_copy in 17 papers adapt.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 93a11f62e4a129f0 · report fixture: signature optimizer:SGD/0/? · returned SGD · level recorded, date not recorded
prototype_weights loss.py ran fingerprinted MIT (permissive) · 1b78e684c8183c16 · report fixture: signature feature:Tensor/2/float, center:Tensor/2/float, bandwidth:Tensor/0/float · returned Tensor · level recorded 2026-09-25
rgb_loader in 16 papers data_list.py ran · honoured contract MIT (permissive) · 2c5ce24ea2b5d2a4 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-22

Tasks

Domain AdaptationSource-Free 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