{"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/architecture-matters-uncovering-implicit-1","title":"Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning","arxiv_id":"2311.02687","date":"2023-11-05","proceeding":"NeurIPS 2023 11","authors":["Xiaojun Guo","Yifei Wang","Zeming Wei","Yisen Wang"],"abstract":"With the prosperity of contrastive learning for visual representation learning (VCL), it is also adapted to the graph domain and yields promising performance. However, through a systematic study of various graph contrastive learning (GCL) methods, we observe that some common phenomena among existing GCL methods that are quite different from the original VCL methods, including 1) positive samples are not a must for GCL; 2) negative samples are not necessary for graph classification, neither for node classification when adopting specific normalization modules; 3) data augmentations have much less influence on GCL, as simple domain-agnostic augmentations (e.g., Gaussian noise) can also attain fairly good performance. By uncovering how the implicit inductive bias of GNNs works in contrastive learning, we theoretically provide insights into the above intriguing properties of GCL. Rather than directly porting existing VCL methods to GCL, we advocate for more attention toward the unique architecture of graph learning and consider its implicit influence when designing GCL methods. Code is available at https: //github.com/PKU-ML/ArchitectureMattersGCL.","url_abs":"https://arxiv.org/abs/2311.02687v1","url_pdf":"https://arxiv.org/pdf/2311.02687v1.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":"architecture-matters-uncovering-implicit-1","repo_url":"https://github.com/pku-ml/architecturemattersgcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"graph-classification","task_name":"Graph Classification"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"representation-learning","task_name":"Representation 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=2311.02687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.02687"}},"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/PKU-ML/ArchitectureMattersGCL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pku-ml/architecturemattersgcl","reach":null}],"summary":{"ran_fixture":3,"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":0,"samples":[{"code_sha256_prefix":"6aebfbe1fa239bbc","entry":"logistic_classify","repo":"PKU-ML/ArchitectureMattersGCL","repo_kind":"official","path":"GCL/GraphCL/evaluate_embedding.py","file_url":"https://github.com/PKU-ML/ArchitectureMattersGCL/blob/HEAD/GCL/GraphCL/evaluate_embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6aebfbe1fa239bbc"}},{"code_sha256_prefix":"6f62b84037b7ba3a","entry":"loss_cl","repo":"PKU-ML/ArchitectureMattersGCL","repo_kind":"official","path":"GCL/AutoGCL/unsupervised/us_main.py","file_url":"https://github.com/PKU-ML/ArchitectureMattersGCL/blob/HEAD/GCL/AutoGCL/unsupervised/us_main.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f62b84037b7ba3a"}},{"code_sha256_prefix":"ed26e617595e3129","entry":"nce_loss","repo":"pku-ml/architecturemattersgcl","repo_kind":"official","path":"GCL/GraphCL/cortex_DIM/functions/dim_losses.py","file_url":"https://github.com/pku-ml/architecturemattersgcl/blob/HEAD/GCL/GraphCL/cortex_DIM/functions/dim_losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed26e617595e3129"}},{"code_sha256_prefix":"2e93ec32d2ba667c","entry":"randomforest_classify","repo":"PKU-ML/ArchitectureMattersGCL","repo_kind":"official","path":"GCL/GraphCL/evaluate_embedding.py","file_url":"https://github.com/PKU-ML/ArchitectureMattersGCL/blob/HEAD/GCL/GraphCL/evaluate_embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e93ec32d2ba667c"}},{"code_sha256_prefix":"ed8e4cd7bf523e6f","entry":"svc_classify","repo":"PKU-ML/ArchitectureMattersGCL","repo_kind":"official","path":"GCL/GraphCL/evaluate_embedding.py","file_url":"https://github.com/PKU-ML/ArchitectureMattersGCL/blob/HEAD/GCL/GraphCL/evaluate_embedding.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed8e4cd7bf523e6f"}},{"code_sha256_prefix":"066824ed5553a7e7","entry":"train_cl","repo":"PKU-ML/ArchitectureMattersGCL","repo_kind":"official","path":"GCL/AutoGCL/unsupervised/us_main.py","file_url":"https://github.com/PKU-ML/ArchitectureMattersGCL/blob/HEAD/GCL/AutoGCL/unsupervised/us_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"066824ed5553a7e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}