{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rethinking-and-scaling-up-graph-contrastive","title":"Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination","arxiv_id":"2206.01535","date":"2022-06-03","proceeding":null,"authors":["Yizhen Zheng","Shirui Pan","Vincent CS Lee","Yu Zheng","Philip S. Yu"],"abstract":"Graph contrastive learning (GCL) alleviates the heavy reliance on label information for graph representation learning (GRL) via self-supervised learning schemes. The core idea is to learn by maximising mutual information for similar instances, which requires similarity computation between two node instances. However, GCL is inefficient in both time and memory consumption. In addition, GCL normally requires a large number of training epochs to be well-trained on large-scale datasets. Inspired by an observation of a technical defect (i.e., inappropriate usage of Sigmoid function) commonly used in two representative GCL works, DGI and MVGRL, we revisit GCL and introduce a new learning paradigm for self-supervised graph representation learning, namely, Group Discrimination (GD), and propose a novel GD-based method called Graph Group Discrimination (GGD). Instead of similarity computation, GGD directly discriminates two groups of node samples with a very simple binary cross-entropy loss. In addition, GGD requires much fewer training epochs to obtain competitive performance compared with GCL methods on large-scale datasets. These two advantages endow GGD with very efficient property. Extensive experiments show that GGD outperforms state-of-the-art self-supervised methods on eight datasets. In particular, GGD can be trained in 0.18 seconds (6.44 seconds including data preprocessing) on ogbn-arxiv, which is orders of magnitude (10,000+) faster than GCL baselines while consuming much less memory. Trained with 9 hours on ogbn-papers100M with billion edges, GGD outperforms its GCL counterparts in both accuracy and efficiency.","url_abs":"https://arxiv.org/abs/2206.01535v2","url_pdf":"https://arxiv.org/pdf/2206.01535v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rethinking-and-scaling-up-graph-contrastive","repo_url":"https://github.com/zyzisastudyreallyhardguy/graph-group-discrimination","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dgi","method_name":"DGI"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.01535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01535"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zyzisastudyreallyhardguy/graph-group-discrimination","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"c0251c2b0a19010a","entry":"aug_feature_dropout","repo":"zyzisastudyreallyhardguy/Graph-Group-Discrimination","repo_kind":"official","path":"GGD_ogbn_arxiv_1epoch/train_arxiv_ready.py","file_url":"https://github.com/zyzisastudyreallyhardguy/Graph-Group-Discrimination/blob/HEAD/GGD_ogbn_arxiv_1epoch/train_arxiv_ready.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0251c2b0a19010a"}},{"code_sha256_prefix":"a8bce308ad932970","entry":"aug_feature_dropout","repo":"zyzisastudyreallyhardguy/Graph-Group-Discrimination","repo_kind":"official","path":"GGD-citation/execute.py","file_url":"https://github.com/zyzisastudyreallyhardguy/Graph-Group-Discrimination/blob/HEAD/GGD-citation/execute.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8bce308ad932970"}},{"code_sha256_prefix":"ff48cfbf50b51f67","entry":"evaluate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ff48cfbf50b51f67"}},{"code_sha256_prefix":"55e2853f190fe060","entry":"evaluate","repo":"zyzisastudyreallyhardguy/Graph-Group-Discrimination","repo_kind":"official","path":"GGD-amco/train_coauthor.py","file_url":"https://github.com/zyzisastudyreallyhardguy/Graph-Group-Discrimination/blob/HEAD/GGD-amco/train_coauthor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55e2853f190fe060"}},{"code_sha256_prefix":"33661bd507a081fa","entry":"aug_random_edge","repo":"zyzisastudyreallyhardguy/Graph-Group-Discrimination","repo_kind":"official","path":"GGD-citation/execute.py","file_url":"https://github.com/zyzisastudyreallyhardguy/Graph-Group-Discrimination/blob/HEAD/GGD-citation/execute.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33661bd507a081fa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}