{"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-dimensional-rationale-in-graph","title":"Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective","arxiv_id":"2312.10401","date":"2023-12-16","proceeding":null,"authors":["Qirui Ji","Jiangmeng Li","Jie Hu","Rui Wang","Changwen Zheng","Fanjiang Xu"],"abstract":"Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://github.com/ByronJi/DRGCL.","url_abs":"https://arxiv.org/abs/2312.10401v3","url_pdf":"https://arxiv.org/pdf/2312.10401v3.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-dimensional-rationale-in-graph","repo_url":"https://github.com/byronji/drgcl","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":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.10401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10401"}},"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/byronji/drgcl","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_draft_wrong":3,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"b822dd00427403bf","entry":"cycle_index","repo":"byronji/drgcl","repo_kind":"official","path":"TransferLearning/bio/pretrain_drgcl.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/TransferLearning/bio/pretrain_drgcl.py","link_basis":"harvester_set","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":"b822dd00427403bf"}},{"code_sha256_prefix":"33da216971e030f9","entry":"drop_nodes","repo":"byronji/drgcl","repo_kind":"official","path":"unsupervised_TU/aug.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/unsupervised_TU/aug.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33da216971e030f9"}},{"code_sha256_prefix":"17ef9103436a92bf","entry":"eval","repo":"byronji/drgcl","repo_kind":"official","path":"TransferLearning/bio/finetune_drgcl.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/TransferLearning/bio/finetune_drgcl.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":"17ef9103436a92bf"}},{"code_sha256_prefix":"5cc1437e6af51bc4","entry":"permute_edges","repo":"byronji/drgcl","repo_kind":"official","path":"unsupervised_TU/aug.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/unsupervised_TU/aug.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5cc1437e6af51bc4"}},{"code_sha256_prefix":"82656aebda7aec5b","entry":"subgraph","repo":"byronji/drgcl","repo_kind":"official","path":"unsupervised_TU/aug.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/unsupervised_TU/aug.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"82656aebda7aec5b"}},{"code_sha256_prefix":"1a09a794a09f3231","entry":"train","repo":"byronji/drgcl","repo_kind":"official","path":"TransferLearning/chem/pretrain_drgcl.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/TransferLearning/chem/pretrain_drgcl.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":"1a09a794a09f3231"}},{"code_sha256_prefix":"9ccb1b88a517c70d","entry":"eval","repo":"byronji/drgcl","repo_kind":"official","path":"TransferLearning/chem/finetune.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/TransferLearning/chem/finetune.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":"9ccb1b88a517c70d"}},{"code_sha256_prefix":"3be1181cc4193845","entry":"train","repo":"byronji/drgcl","repo_kind":"official","path":"TransferLearning/bio/pretrain_drgcl.py","file_url":"https://github.com/byronji/drgcl/blob/HEAD/TransferLearning/bio/pretrain_drgcl.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":"3be1181cc4193845"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}