Papers › Enhancing Domain Adaptation through Prompt Gradient Alignment

Enhancing Domain Adaptation through Prompt Gradient Alignment

13 Jun 2024arXiv:2406.09353archive 2025-07-28

Hoang Phan, Lam Tran, Quyen Tran, Trung Le

Prior Unsupervised Domain Adaptation (UDA) methods often aim to train a domain-invariant feature extractor, which may hinder the model from learning sufficiently discriminative features. To tackle this, a line of works based on prompt learning leverages the power of large-scale pre-trained vision-language models to learn both domain-invariant and specific features through a set of domain-agnostic and domain-specific learnable prompts. Those studies typically enforce invariant constraints on representation, output, or prompt space to learn such prompts. In contrast, we cast UDA as a multiple-objective optimization problem in which each objective is represented by a domain loss. Under this new framework, we propose to align per-objective gradients to foster consensus between them. Additionally, to prevent potential overfitting when fine-tuning this deep learning architecture, we penalize the norm of these gradients. To achieve these goals, we devise a practical gradient update procedure that can work under both single-source and multi-source UDA. Empirically, our method consistently outperforms other vision-language model adaptation methods. The implementation is available at https://github.com/VietHoang1512/PGA.

PaperPDFCodeCode 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="2406.09353")

Code

Syntology Ran 6 of 12 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

viethoang1512/pga officialmentioned in paperpytorch 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

12 samples harvested; 6 ran; 1 honoured the contract we drafted; 6 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.

1ran · honoured contract
1ran · our draft was wrong
4ran
6unverified

Licence: 12 of the 12 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 VietHoang1512/PGA. “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.

check_isfile VietHoang1512/PGA/LA/dataset.py official repository ran no licence file found · pointer only · f1188d085e216ee3 · report
entropy_loss viethoang1512/pga/LA/main_uda.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · bf4375591fccddac · report
load_data VietHoang1512/PGA/LA/dataloader.py official repository ran no licence file found · pointer only · 1d67fe6fb333ae8e · report
load_svhn VietHoang1512/PGA/LA/digit5.py official repository ran no licence file found · pointer only · f6df3bd3264e9f51 · report
read_image VietHoang1512/PGA/LA/dataset.py official repository ran no licence file found · pointer only · 7a92bf4975eb29ec · report
test viethoang1512/pga/LA/main_uda.py official repository ran · honoured contract no licence file found · pointer only · 6301fb5daaeef4c9 · report
build_model VietHoang1512/PGA/LA/clip_custom/model.py official repository unverified no licence file found · pointer only · 40418fa224950340 · report
get_confirm_token VietHoang1512/PGA/download.py official repository unverified no licence file found · pointer only · 135b3dc835ffe6ad · report
get_google_drive_stream VietHoang1512/PGA/download.py official repository unverified no licence file found · pointer only · 7de13fad99cbd042 · report
listdir_nohidden VietHoang1512/PGA/LA/dataset.py official repository unverified no licence file found · pointer only · fe317c3d4d24147a · report
load_mnist VietHoang1512/PGA/LA/digit5.py official repository unverified no licence file found · pointer only · 342c0c85275110c4 · report
load_mnist_m VietHoang1512/PGA/LA/digit5.py official repository unverified no licence file found · pointer only · 46957f35cb27059c · report

Tasks

Domain AdaptationLanguage ModelingLanguage ModellingMulti-Source Unsupervised Domain AdaptationPrompt LearningUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Office-Home PGA (ViT-L/14) Accuracy 89.4 #3 of 29 Archive leaderboard report
Domain Adaptation Office-Home PGA (ViT-B/16) Accuracy 85.1 #7 of 29 Archive leaderboard report
Domain Adaptation Office-Home PGA (RN50) Accuracy 75.8 #11 of 29 Archive leaderboard report
Domain Adaptation S2RDA-49 PGA Accuracy 74.1 #1 of 1 Archive leaderboard report
Domain Adaptation S2RDA-MS-39 PGA Accuracy 38 #1 of 1 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.

Methods

Introduced by this paper: MPGA, PGA

ALIGNMPGAPGA

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