{"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/perfect-alignment-may-be-poisonous-to-graph","title":"Perfect Alignment May be Poisonous to Graph Contrastive Learning","arxiv_id":"2310.03977","date":"2023-10-06","proceeding":null,"authors":["Jingyu Liu","Huayi Tang","Yong liu"],"abstract":"Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones. However, few of researchers have focused on the inner law behind specific augmentations used in graph-based learning. What kind of augmentation will help downstream performance, how does contrastive learning actually influence downstream tasks, and why the magnitude of augmentation matters so much? This paper seeks to address these questions by establishing a connection between augmentation and downstream performance. Our findings reveal that GCL contributes to downstream tasks mainly by separating different classes rather than gathering nodes of the same class. So perfect alignment and augmentation overlap which draw all intra-class samples the same can not fully explain the success of contrastive learning. Therefore, in order to understand how augmentation aids the contrastive learning process, we conduct further investigations into the generalization, finding that perfect alignment that draw positive pair the same could help contrastive loss but is poisonous to generalization, as a result, perfect alignment may not lead to best downstream performance, so specifically designed augmentation is needed to achieve appropriate alignment performance and improve downstream accuracy. We further analyse the result by information theory and graph spectrum theory and propose two simple but effective methods to verify the theories. The two methods could be easily applied to various GCL algorithms and extensive experiments are conducted to prove its effectiveness. The code is available at https://github.com/somebodyhh1/GRACEIS","url_abs":"https://arxiv.org/abs/2310.03977v3","url_pdf":"https://arxiv.org/pdf/2310.03977v3.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":"perfect-alignment-may-be-poisonous-to-graph","repo_url":"https://github.com/somebodyhh1/graceis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.03977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03977"}},"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":"deterministic:regex_extraction","url":"https://github.com/somebodyhh1/GRACEIS","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/somebodyhh1/graceis","reach":{"status":"ok"}}],"summary":{"ran":4,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":"a9ad6a42fc6393d7","entry":"compute_cam","repo":"somebodyhh1/GRACEIS","repo_kind":"official","path":"mask.py","file_url":"https://github.com/somebodyhh1/GRACEIS/blob/HEAD/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9ad6a42fc6393d7"}},{"code_sha256_prefix":"ec135d55c3e0e7d2","entry":"drop_edge","repo":"somebodyhh1/GRACEIS","repo_kind":"official","path":"mask.py","file_url":"https://github.com/somebodyhh1/GRACEIS/blob/HEAD/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ec135d55c3e0e7d2"}},{"code_sha256_prefix":"22bfb6129463d322","entry":"drop_feature","repo":"somebodyhh1/GRACEIS","repo_kind":"official","path":"model.py","file_url":"https://github.com/somebodyhh1/GRACEIS/blob/HEAD/model.py","link_basis":"harvester_set","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":"22bfb6129463d322"}},{"code_sha256_prefix":"5b18ad957d4c29e1","entry":"get_path","repo":"somebodyhh1/GRACEIS","repo_kind":"official","path":"dataset.py","file_url":"https://github.com/somebodyhh1/GRACEIS/blob/HEAD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5b18ad957d4c29e1"}},{"code_sha256_prefix":"1b4a3fc2148ab0e2","entry":"normalize","repo":"somebodyhh1/GRACEIS","repo_kind":"official","path":"mask.py","file_url":"https://github.com/somebodyhh1/GRACEIS/blob/HEAD/mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b4a3fc2148ab0e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}