{"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/algorithmic-concept-based-explainable","title":"Algorithmic Concept-based Explainable Reasoning","arxiv_id":"2107.07493","date":"2021-07-15","proceeding":null,"authors":["Dobrik Georgiev","Pietro Barbiero","Dmitry Kazhdan","Petar Veličković","Pietro Liò"],"abstract":"Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems. This has numerous benefits, such as allowing applications of algorithms when preconditions are not satisfied, or reusing learned models when sufficient training data is not available or can't be generated. Unfortunately, a key hindrance of these approaches is their lack of explainability, since GNNs are black-box models that cannot be interpreted directly. In this work, we address this limitation by applying existing work on concept-based explanations to GNN models. We introduce concept-bottleneck GNNs, which rely on a modification to the GNN readout mechanism. Using three case studies we demonstrate that: (i) our proposed model is capable of accurately learning concepts and extracting propositional formulas based on the learned concepts for each target class; (ii) our concept-based GNN models achieve comparative performance with state-of-the-art models; (iii) we can derive global graph concepts, without explicitly providing any supervision on graph-level concepts.","url_abs":"https://arxiv.org/abs/2107.07493v1","url_pdf":"https://arxiv.org/pdf/2107.07493v1.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":"algorithmic-concept-based-explainable","repo_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2107.07493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07493"}},"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/HekpoMaH/algorithmic-concepts-reasoning","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"ran":0,"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":"b727498f1bd070ef","entry":"alphanum_key","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/datasets.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/datasets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b727498f1bd070ef"}},{"code_sha256_prefix":"a50d15c7b56af0c9","entry":"flip_edge_index","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/utils.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a50d15c7b56af0c9"}},{"code_sha256_prefix":"3bf0dd9d6e97ce05","entry":"float2bin2","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/layers/encoders.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/layers/encoders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3bf0dd9d6e97ce05"}},{"code_sha256_prefix":"d0592ccf63085d1a","entry":"float2bitstring","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/layers/encoders.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/layers/encoders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d0592ccf63085d1a"}},{"code_sha256_prefix":"53a66a2edc77a464","entry":"generate_random_graph","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/deterministic/BFS.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/deterministic/BFS.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53a66a2edc77a464"}},{"code_sha256_prefix":"a8e595421bb2362f","entry":"get_concept_labels","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/plot_per_epoch.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/plot_per_epoch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a8e595421bb2362f"}},{"code_sha256_prefix":"cc2e10bf435de0ef","entry":"line_count","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/plot_per_epoch.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/plot_per_epoch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc2e10bf435de0ef"}},{"code_sha256_prefix":"5deae6e8373498ab","entry":"uint322bitstring","repo":"HekpoMaH/algorithmic-concepts-reasoning","repo_kind":"official","path":"algos/layers/encoders.py","file_url":"https://github.com/HekpoMaH/algorithmic-concepts-reasoning/blob/HEAD/algos/layers/encoders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5deae6e8373498ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}