Papers › Efficient Domain Generalization via Common-Specific Low-Rank Decomposition

Efficient Domain Generalization via Common-Specific Low-Rank Decomposition

28 Mar 2020ICML 2020 1arXiv:2003.12815archive 2025-07-28

Vihari Piratla, Praneeth Netrapalli, Sunita Sarawagi

Domain generalization refers to the task of training a model which generalizes to new domains that are not seen during training. We present CSD (Common Specific Decomposition), for this setting,which jointly learns a common component (which generalizes to new domains) and a domain specific component (which overfits on training domains). The domain specific components are discarded after training and only the common component is retained. The algorithm is extremely simple and involves only modifying the final linear classification layer of any given neural network architecture. We present a principled analysis to understand existing approaches, provide identifiability results of CSD,and study effect of low-rank on domain generalization. We show that CSD either matches or beats state of the art approaches for domain generalization based on domain erasure, domain perturbed data augmentation, and meta-learning. Further diagnostics on rotated MNIST, where domains are interpretable, confirm the hypothesis that CSD successfully disentangles common and domain specific components and hence leads to better domain generalization.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2003.12815")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: official repository: 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

vihari/csd officialmentioned in papermentioned on GitHubpytorchMIT 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; 0 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

11unverified

Licence: 0 of the 11 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 vihari/csd. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

alexnet vihari/csd/pacs/models/alexnet.py official repository unverified MIT (permissive) · 81b32462156333ce · report
custom_rot vihari/csd/rotation/ResNet.py official repository unverified MIT (permissive) · 639603695957f436 · report
load_data vihari/csd/hw/lipitk.py official repository unverified MIT (permissive) · 7867292780cc60d7 · report
load_data vihari/csd/hw/nhcd.py official repository unverified MIT (permissive) · ff5baf06d230e98a · report
one_hot vihari/csd/pacs/train_csd.py official repository unverified MIT (permissive) · ded0bf1e1b21f399 · report
prepare_data vihari/csd/hw/lipitk.py official repository unverified MIT (permissive) · 317da15047e473d1 · report
prepare_data vihari/csd/hw/rmnist.py official repository unverified MIT (permissive) · a8669f97e275a295 · report
prepare_data_for vihari/csd/hw/rmnist.py official repository unverified MIT (permissive) · 6ab3b3ea2d111f68 · report
rankL vihari/csd/speech/losses.py official repository unverified MIT (permissive) · a3dee273f5549710 · report
training vihari/csd/hw/nhcd.py official repository unverified MIT (permissive) · 59c9109a03787bbe · report
warp_loss vihari/csd/speech/losses.py official repository unverified MIT (permissive) · 5e2641cdd55e645c · report

Tasks

Data AugmentationDomain GeneralizationMeta-LearningRotated MNIST

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization LipitK CSD (Ours) Accuracy 87.3 #1 of 1 Archive leaderboard report
Domain Generalization PACS CSD (Resnet-18) Average Accuracy 80.69 #93 of 133 Archive leaderboard report
Domain Generalization Rotated Fashion-MNIST CSD Accuracy 78.9 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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