{"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/analyzing-data-centric-properties-for","title":"Analyzing Data-Centric Properties for Graph Contrastive Learning","arxiv_id":"2208.02810","date":"2022-08-04","proceeding":null,"authors":["Puja Trivedi","Ekdeep Singh Lubana","Mark Heimann","Danai Koutra","Jayaraman J. Thiagarajan"],"abstract":"Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semantics, separability of classes in some latent space, and recoverability of labels from augmented samples. However, given their discrete, non-Euclidean nature, graph datasets and graph SSL methods are unlikely to satisfy these properties. This raises the question: how do graph SSL methods, such as contrastive learning (CL), work well? To systematically probe this question, we perform a generalization analysis for CL when using generic graph augmentations (GGAs), with a focus on data-centric properties. Our analysis yields formal insights into the limitations of GGAs and the necessity of task-relevant augmentations. As we empirically show, GGAs do not induce task-relevant invariances on common benchmark datasets, leading to only marginal gains over naive, untrained baselines. Our theory motivates a synthetic data generation process that enables control over task-relevant information and boasts pre-defined optimal augmentations. This flexible benchmark helps us identify yet unrecognized limitations in advanced augmentation techniques (e.g., automated methods). Overall, our work rigorously contextualizes, both empirically and theoretically, the effects of data-centric properties on augmentation strategies and learning paradigms for graph SSL.","url_abs":"https://arxiv.org/abs/2208.02810v3","url_pdf":"https://arxiv.org/pdf/2208.02810v3.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":"analyzing-data-centric-properties-for","repo_url":"https://github.com/pujacomputes/datapropsgraphssl","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":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.02810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02810"}},"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/pujacomputes/datapropsgraphSSL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pujacomputes/datapropsgraphssl","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran_honours":2,"unverified":3},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"5021b9765af13b73","entry":"attach_motif","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5021b9765af13b73"}},{"code_sha256_prefix":"5bdaecd839af62f3","entry":"compute_sep","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"examples/compute_invariance_sep.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/examples/compute_invariance_sep.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bdaecd839af62f3"}},{"code_sha256_prefix":"89a4d235cfbcb6be","entry":"get_host_cands","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.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":"89a4d235cfbcb6be"}},{"code_sha256_prefix":"938830ef2b180441","entry":"pairwise_cos","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"examples/compute_invariance_sep.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/examples/compute_invariance_sep.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"938830ef2b180441"}},{"code_sha256_prefix":"c5c43465c498efee","entry":"random_ba","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c5c43465c498efee"}},{"code_sha256_prefix":"6fe9689ed3b012d4","entry":"add_to_list","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6fe9689ed3b012d4"}},{"code_sha256_prefix":"b79b228917c3479a","entry":"make_class_dataset","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b79b228917c3479a"}},{"code_sha256_prefix":"32861c24d95bf2ae","entry":"random_tree","repo":"pujacomputes/datapropsgraphssl","repo_kind":"official","path":"datagen/create_dataset.py","file_url":"https://github.com/pujacomputes/datapropsgraphssl/blob/HEAD/datagen/create_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32861c24d95bf2ae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}