{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/same-uncovering-gnn-black-box-with-structure","title":"SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations","arxiv_id":null,"date":"2023-09-21","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Post-hoc explanation techniques on graph neural networks (GNNs) provide economical solutions for opening the black-box graph models without model retraining. Many GNN explanation variants have achieved state-of-the-art explaining results on a diverse set of benchmarks, while they rarely provide theoretical analysis for their inherent properties and explanatory capability. In this work, we propose $\\underline{\\text{S}}$tructure-$\\underline{\\text{A}}$ware Shapley-based $\\underline{\\text{M}}$ultipiece $\\underline{\\text{E}}$xplanation (SAME) method to address the structure-aware feature interactions challenges for GNNs explanation. Specifically, SAME leverages an expansion-based Monte Carlo tree search to explore the multi-grained structure-aware connected substructure. Afterward, the explanation results are encouraged to be informative of the graph properties by optimizing the combination of distinct single substructures. With the consideration of fair feature interactions in the process of investigating multiple connected important substructures, the explanation provided by SAME has the potential to be as explainable as the theoretically optimal explanation obtained by the Shapley value within polynomial time. Extensive experiments on real-world and synthetic benchmarks show that SAME improves the previous state-of-the-art fidelity performance by 12.9\\% on BBBP, 7.01\\% on MUTAG, 42.3\\% on Graph-SST2, 38.9\\% on Graph-SST5, 11.3\\% on BA-2Motifs and 18.2\\% on BA-Shapes under the same testing condition. Code is available at https://github.com/same2023neurips/same.Submission Number: 12143","url_abs":"https://openreview.net/forum?id=kBBsj9KRgh","url_pdf":"https://openreview.net/pdf?id=kBBsj9KRgh","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":"same-uncovering-gnn-black-box-with-structure","repo_url":"https://github.com/same2023neurips/same","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"explanation-fidelity-evaluation","task_name":"Explanation Fidelity Evaluation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/explanation-fidelity-evaluation-on-ba-2motifs","task":"Explanation Fidelity Evaluation","dataset":"BA-2motifs","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.549"},"uses_additional_data":false},{"leaderboard":"/sota/explanation-fidelity-evaluation-on-ba-shapes","task":"Explanation Fidelity Evaluation","dataset":"BA-Shapes","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.214"},"uses_additional_data":false},{"leaderboard":"/sota/explanation-fidelity-evaluation-on-bbbp","task":"Explanation Fidelity Evaluation","dataset":"BBBP","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.489"},"uses_additional_data":false},{"leaderboard":"/sota/explanation-fidelity-evaluation-on-mutag","task":"Explanation Fidelity Evaluation","dataset":"MUTAG","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.702"},"uses_additional_data":false},{"leaderboard":"/sota/explanation-fidelity-evaluation-on-sst-5","task":"Explanation Fidelity Evaluation","dataset":"SST-5","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.393"},"uses_additional_data":false},{"leaderboard":"/sota/explanation-fidelity-evaluation-on-sst2","task":"Explanation Fidelity Evaluation","dataset":"SST2","model":"GCN","rank_in_archive_order":1,"of":1,"metrics":{"fidelity":"0.373"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"no_arxiv_id","checked_against":null,"by_repo":[{"repo":"same2023neurips/same","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"dd68d267236db9b0b321ea359a20842c4c2dcbe9f07bb5eb8c103230add28140","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}