{"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/discovering-invariant-rationales-for-graph-1","title":"Discovering Invariant Rationales for Graph Neural Networks","arxiv_id":"2201.12872","date":"2022-01-30","proceeding":"ICLR 2022 4","authors":["Ying-Xin Wu","Xiang Wang","An Zhang","Xiangnan He","Tat-Seng Chua"],"abstract":"Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features -- rationale -- which guides the model prediction. Unfortunately, the leading rationalization models often rely on data biases, especially shortcut features, to compose rationales and make predictions without probing the critical and causal patterns. Moreover, such data biases easily change outside the training distribution. As a result, these models suffer from a huge drop in interpretability and predictive performance on out-of-distribution data. In this work, we propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs. It conducts interventions on the training distribution to create multiple interventional distributions. Then it approaches the causal rationales that are invariant across different distributions while filtering out the spurious patterns that are unstable. Experiments on both synthetic and real-world datasets validate the superiority of our DIR in terms of interpretability and generalization ability on graph classification over the leading baselines. Code and datasets are available at https://github.com/Wuyxin/DIR-GNN.","url_abs":"https://arxiv.org/abs/2201.12872v1","url_pdf":"https://arxiv.org/pdf/2201.12872v1.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":"discovering-invariant-rationales-for-graph-1","repo_url":"https://github.com/wuyxin/dir-gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-classification","task_name":"Graph Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.12872","atlas_url":"https://app.syntology.ai/?focus=2201.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12872"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Wuyxin/DIR-GNN","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wuyxin/dir-gnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"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":0,"samples":[{"code_sha256_prefix":"e3ffbd6a2bf78a6b","entry":"relabel","repo":"wuyxin/dir-gnn","repo_kind":"official","path":"train/spmotif_dir.py","file_url":"https://github.com/wuyxin/dir-gnn/blob/HEAD/train/spmotif_dir.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":"e3ffbd6a2bf78a6b"}},{"code_sha256_prefix":"496db6912d4f2482","entry":"split_batch","repo":"wuyxin/dir-gnn","repo_kind":"official","path":"train/spmotif_dir.py","file_url":"https://github.com/wuyxin/dir-gnn/blob/HEAD/train/spmotif_dir.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"496db6912d4f2482"}},{"code_sha256_prefix":"f293b85d11372c06","entry":"split_graph","repo":"wuyxin/dir-gnn","repo_kind":"official","path":"train/spmotif_dir.py","file_url":"https://github.com/wuyxin/dir-gnn/blob/HEAD/train/spmotif_dir.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":"f293b85d11372c06"}},{"code_sha256_prefix":"e89899286379a3a5","entry":"CausalAttNet","repo":"wuyxin/dir-gnn","repo_kind":"official","path":"train/spmotif_dir.py","file_url":"https://github.com/wuyxin/dir-gnn/blob/HEAD/train/spmotif_dir.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e89899286379a3a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}