Papers › GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning

GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning

9 Nov 2023arXiv:2311.05729archive 2025-07-28

Guangyue Xu, Joyce Chai, Parisa Kordjamshidi

Pre-trained vision-language models (VLMs) have achieved promising success in many fields, especially with prompt learning paradigm. In this work, we propose GIP-COL (Graph-Injected Soft Prompting for COmpositional Learning) to better explore the compositional zero-shot learning (CZSL) ability of VLMs within the prompt-based learning framework. The soft prompt in GIPCOL is structured and consists of the prefix learnable vectors, attribute label and object label. In addition, the attribute and object labels in the soft prompt are designated as nodes in a compositional graph. The compositional graph is constructed based on the compositional structure of the objects and attributes extracted from the training data and consequently feeds the updated concept representation into the soft prompt to capture this compositional structure for a better prompting for CZSL. With the new prompting strategy, GIPCOL achieves state-of-the-art AUC results on all three CZSL benchmarks, including MIT-States, UT-Zappos, and C-GQA datasets in both closed and open settings compared to previous non-CLIP as well as CLIP-based methods. We analyze when and why GIPCOL operates well given the CLIP backbone and its training data limitations, and our findings shed light on designing more effective prompts for CZSL

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="2311.05729")

Code

Syntology Ran 7 of 12 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

hlr/gipcol officialmentioned in papermentioned on GitHubpytorch 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; 7 ran; 0 honoured the contract we drafted; 5 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.

7ran
5unverified

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 hlr/gipcol. “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.

build_lr_scheduler hlr/gipcol/Models/CoopModel/Scheduler/lr_scheduler.py official repository ran no licence file found · pointer only · a23cf5bf1e4b1696 · report
build_optimizer_from_coop hlr/gipcol/Models/CoopModel/Optimizer/optimizer.py official repository ran no licence file found · pointer only · b9bd2410ef8caf6a · report
compute_cosine_similarity hlr/gipcol/DataSet/compute_feasibility.py official repository ran no licence file found · pointer only · f104560916c04c5d · report
compute_representations hlr/gipcol/script_shared_evaluator_from_csp.py official repository ran no licence file found · pointer only · 3d6ee201ac8ba1db · report
imagenet_transform hlr/gipcol/DataSet/AttrOpCompDataSet.py official repository ran no licence file found · pointer only · dd9bca67df4ae7b8 · report
load_glove_embeddings hlr/gipcol/DataSet/compute_feasibility.py official repository ran no licence file found · pointer only · 9a62704a729580fc · report
predict_logits hlr/gipcol/script_shared_evaluator_from_csp.py official repository ran no licence file found · pointer only · 6bddc3dfac41ae6c · report
build_model hlr/gipcol/Models/CoopModel/clip/model.py official repository unverified no licence file found · pointer only · c47aa9e5b049a11d · report
build_optimizer hlr/gipcol/Models/CoopModel/Optimizer/optimizer.py official repository unverified no licence file found · pointer only · 6c217fe4e4e0585d · report
clip_baseline hlr/gipcol/script_shared_evaluator_from_csp.py official repository unverified no licence file found · pointer only · 8bfeb91e02c5cca9 · report
load hlr/gipcol/Models/CoopModel/clip/clip.py official repository unverified no licence file found · pointer only · fbf8c0143d9c48e3 · report
train_model hlr/gipcol/script_train_graph_prompt.py official repository unverified no licence file found · pointer only · b5a52229ba9f8344 · report

Tasks

AttributeCompositional Zero-Shot LearningPrompt LearningZero-Shot Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

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