Papers › Towards Data-Free Domain Generalization

Towards Data-Free Domain Generalization

9 Oct 2021arXiv:2110.04545archive 2025-07-28

Ahmed Frikha, Haokun Chen, Denis Krompaß, Thomas Runkler, Volker Tresp

In this work, we investigate the unexplored intersection of domain generalization (DG) and data-free learning. In particular, we address the question: How can knowledge contained in models trained on different source domains be merged into a single model that generalizes well to unseen target domains, in the absence of source and target domain data? Machine learning models that can cope with domain shift are essential for real-world scenarios with often changing data distributions. Prior DG methods typically rely on using source domain data, making them unsuitable for private decentralized data. We define the novel problem of Data-Free Domain Generalization (DFDG), a practical setting where models trained on the source domains separately are available instead of the original datasets, and investigate how to effectively solve the domain generalization problem in that case. We propose DEKAN, an approach that extracts and fuses domain-specific knowledge from the available teacher models into a student model robust to domain shift. Our empirical evaluation demonstrates the effectiveness of our method which achieves first state-of-the-art results in DFDG by significantly outperforming data-free knowledge distillation and ensemble baselines.

PaperPDFCodeCode 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 20 code samples harvested from 1 repository linked to this paper: 15 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 15 ran (7 with no instrument failure; 8 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.

HaokunChen245/DFDG officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 15 ran (8 instrument-failed) · 5 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

20 samples harvested: 15 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 5 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
7ran · our draft was wrong
1ran; the contract check could not run
5ran
5unverified

Licence: 0 of the 20 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 HaokunChen245/DFDG. “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.

HaokunChen245/DFDG official repository 20 samples, 15 ran (8 instrument-failed) · 5 unverified
MNISTM dfdg/training/train_student_syn_img.py ran Apache-2.0 (permissive) · cd7b9603cbce6487 · report fixture: returned MNISTM · level recorded 2026-09-22
OfficeHome dfdg/training/train_student_syn_img.py ran Apache-2.0 (permissive) · 52e13479de87ebea · report fixture: returned OfficeHome · level recorded 2026-09-22
PACS dfdg/training/train_student_syn_img.py ran Apache-2.0 (permissive) · c8899dbd625b82a7 · report fixture: returned PACS · level recorded 2026-09-22
VLCS dfdg/training/train_student_syn_img.py ran Apache-2.0 (permissive) · 7988844fd79a2a10 · report fixture: returned VLCS · level recorded 2026-09-22
evaluate_oneset dfdg/training/train_student_syn_img.py ran · honoured contract Apache-2.0 (permissive) · bf5c752f1fdd2344 · report fixture: signature model:callable/0/?, loader:list/1/tuple · returned float · level recorded 2026-09-22
get_abbr_map dfdg/training/train_student_syn_img.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 7e028dd7cef44939 · report fixture: signature dataset:str/0/str · returned dict · level recorded 2026-09-22
get_class_names in 8 papers dfdg/training/train_student_syn_img.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 38e9002eb1f23978 · report fixture: signature dataset:str/0/str · returned list · level recorded 2026-09-22
get_class_number dfdg/training/train_student_syn_img.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 068a32afcb1a875d · report fixture: signature dataset:str/0/str · returned int · level recorded 2026-09-22
get_net in 8 papers dfdg/training/train_student_syn_img.py ran · our draft was wrong Apache-2.0 (permissive) · 9966b8ec681f4404 · report fixture: signature backbone:str/0/str, num_class:int/0/int, pretrained:bool/0/bool, load_path:NoneType/0/? · returned ResNet · level recorded 2026-09-22
get_source_domains dfdg/training/train_student_syn_img.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 56fb6475cb294744 · report fixture: signature dataset:str/0/str · returned list · level recorded 2026-09-22
get_source_domains_abbr dfdg/training/train_student_syn_img.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 32c7347d3ae61759 · report fixture: signature dataset:str/0/str · returned list · level recorded 2026-09-22
kl_loss in 37 papers
census: 8 implementations from 11 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
dfdg/training/train_student_syn_img.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 7ee01bf5efd50d92 · report fixture: signature y:Tensor/2/float, teacher_scores:Tensor/2/float, temp:int/0/int, softmax_applied:bool/0/bool · returned Tensor · level recorded 2026-09-22
lr_cosine_policy dfdg/training/train_student_syn_img.py ran · our draft was wrong Apache-2.0 (permissive) · 9fd6750328ee3f9a · report fixture: signature base_lr:float/0/float, warmup_length:int/0/int, epochs:int/0/int · returned function · level recorded 2026-09-22
lr_policy in 6 papers dfdg/training/train_student_syn_img.py ran · our draft was wrong Apache-2.0 (permissive) · 8879e55d89cdc808 · report fixture: signature lr_fn:callable/0/? · returned function · level recorded 2026-09-22
miniDomainNet dfdg/training/train_student_syn_img.py ran Apache-2.0 (permissive) · 1bf3b903e2947d69 · report fixture: returned miniDomainNet · level recorded 2026-09-22
BaseDataset in 5 papers dfdg/training/train_student_syn_img.py unverified Apache-2.0 (permissive) · bbd4ba6ba7e4b9d1 · report
Digits dfdg/training/train_student_syn_img.py unverified Apache-2.0 (permissive) · 0f3ead3a52a4792f · report
FAKE dfdg/training/train_student_syn_img.py unverified Apache-2.0 (permissive) · 302b7a0d15a99b07 · report
get_dataset in 285 papers dfdg/training/train_student_syn_img.py unverified Apache-2.0 (permissive) · 18be128efd090a2d · report
train_student_syn_img dfdg/training/train_student_syn_img.py unverified Apache-2.0 (permissive) · 307f729c69e1ba8f · 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 DEKAN (graph method: DEKAN). 20 bricks; individually on a fixture: 15 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. train_student_syn_img entry · level 0 · unverified · 307f729c69e1ba8f
  2. FAKE helper · level 0 · unverified · 302b7a0d15a99b07
  3. evaluate_oneset helper · level 1 · ran · honoured contract · bf5c752f1fdd2344
  4. get_class_number helper · level 1 · ran · honoured contract · 068a32afcb1a875d
  5. get_dataset helper · level 0 · unverified · 18be128efd090a2d
  6. get_net helper · level 1 · ran · our draft was wrong · 9966b8ec681f4404
  7. get_source_domains helper · level 1 · ran · our draft was wrong · 56fb6475cb294744
  8. kl_loss helper · level 1 · ran; the contract check could not run (RAISES) · 7ee01bf5efd50d92
  9. lr_cosine_policy helper · level 1 · ran · our draft was wrong · 9fd6750328ee3f9a
  10. get_abbr_map helper · level 1 · ran · our draft was wrong · 7e028dd7cef44939
  11. get_class_names helper · level 1 · ran · our draft was wrong · 38e9002eb1f23978
  12. get_source_domains_abbr helper · level 1 · ran · our draft was wrong · 32c7347d3ae61759
  13. Digits helper · level 0 · unverified · 0f3ead3a52a4792f
  14. OfficeHome helper · level 1 · ran · 52e13479de87ebea
  15. PACS helper · level 1 · ran · c8899dbd625b82a7
  16. VLCS helper · level 1 · ran · 7988844fd79a2a10
  17. miniDomainNet helper · level 1 · ran · 1bf3b903e2947d69
  18. lr_policy helper · level 1 · ran · our draft was wrong · 8879e55d89cdc808
  19. BaseDataset helper · level 0 · unverified · bbd4ba6ba7e4b9d1
  20. MNISTM helper · level 1 · ran · cd7b9603cbce6487

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="2110.04545") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data-free Knowledge DistillationDomain GeneralizationKnowledge Distillation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge Distillation

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