{"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/global-concept-based-interpretability-for","title":"Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis","arxiv_id":"2208.10609","date":"2022-08-22","proceeding":null,"authors":["Han Xuanyuan","Pietro Barbiero","Dobrik Georgiev","Lucie Charlotte Magister","Pietro Lió"],"abstract":"Graph neural networks (GNNs) are highly effective on a variety of graph-related tasks; however, they lack interpretability and transparency. Current explainability approaches are typically local and treat GNNs as black-boxes. They do not look inside the model, inhibiting human trust in the model and explanations. Motivated by the ability of neurons to detect high-level semantic concepts in vision models, we perform a novel analysis on the behaviour of individual GNN neurons to answer questions about GNN interpretability, and propose new metrics for evaluating the interpretability of GNN neurons. We propose a novel approach for producing global explanations for GNNs using neuron-level concepts to enable practitioners to have a high-level view of the model. Specifically, (i) to the best of our knowledge, this is the first work which shows that GNN neurons act as concept detectors and have strong alignment with concepts formulated as logical compositions of node degree and neighbourhood properties; (ii) we quantitatively assess the importance of detected concepts, and identify a trade-off between training duration and neuron-level interpretability; (iii) we demonstrate that our global explainability approach has advantages over the current state-of-the-art -- we can disentangle the explanation into individual interpretable concepts backed by logical descriptions, which reduces potential for bias and improves user-friendliness.","url_abs":"https://arxiv.org/abs/2208.10609v2","url_pdf":"https://arxiv.org/pdf/2208.10609v2.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":"global-concept-based-interpretability-for","repo_url":"https://github.com/xuyhan/gnn-dissect","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.10609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10609"}},"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/xuyhan/gnn-dissect","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"4bf17a2195eb4538","entry":"by_weight","repo":"xuyhan/gnn-dissect","repo_kind":"official","path":"src/concept_ranker.py","file_url":"https://github.com/xuyhan/gnn-dissect/blob/HEAD/src/concept_ranker.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":"4bf17a2195eb4538"}},{"code_sha256_prefix":"7a49c09313de39aa","entry":"by_weight_adv","repo":"xuyhan/gnn-dissect","repo_kind":"official","path":"src/concept_ranker.py","file_url":"https://github.com/xuyhan/gnn-dissect/blob/HEAD/src/concept_ranker.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":"7a49c09313de39aa"}},{"code_sha256_prefix":"40782d8aec1081b1","entry":"by_weight_x_val","repo":"xuyhan/gnn-dissect","repo_kind":"official","path":"src/concept_ranker.py","file_url":"https://github.com/xuyhan/gnn-dissect/blob/HEAD/src/concept_ranker.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":"40782d8aec1081b1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}