{"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/efficient-subgraph-gnns-by-learning-effective","title":"Efficient Subgraph GNNs by Learning Effective Selection Policies","arxiv_id":"2310.20082","date":"2023-10-30","proceeding":null,"authors":["Beatrice Bevilacqua","Moshe Eliasof","Eli Meirom","Bruno Ribeiro","Haggai Maron"],"abstract":"Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs. Unfortunately, their applicability is hampered by the computational complexity associated with performing message passing on many subgraphs. In this paper, we consider the problem of learning to select a small subset of the large set of possible subgraphs in a data-driven fashion. We first motivate the problem by proving that there are families of WL-indistinguishable graphs for which there exist efficient subgraph selection policies: small subsets of subgraphs that can already identify all the graphs within the family. We then propose a new approach, called Policy-Learn, that learns how to select subgraphs in an iterative manner. We prove that, unlike popular random policies and prior work addressing the same problem, our architecture is able to learn the efficient policies mentioned above. Our experimental results demonstrate that Policy-Learn outperforms existing baselines across a wide range of datasets.","url_abs":"https://arxiv.org/abs/2310.20082v2","url_pdf":"https://arxiv.org/pdf/2310.20082v2.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":"efficient-subgraph-gnns-by-learning-effective","repo_url":"https://github.com/beabevi/policy-learn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.20082","atlas_url":"https://app.syntology.ai/?focus=2310.20082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20082"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/beabevi/policy-learn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"c6920406a0f53f26","entry":"lengths2slices","repo":"beabevi/policy-learn","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c6920406a0f53f26"}},{"code_sha256_prefix":"2e56a3afa91eb04e","entry":"observation_coos","repo":"beabevi/policy-learn","repo_kind":"official","path":"observation.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/observation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e56a3afa91eb04e"}},{"code_sha256_prefix":"e5f2de0d3aba87a7","entry":"observation_to","repo":"beabevi/policy-learn","repo_kind":"official","path":"observation.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/observation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e5f2de0d3aba87a7"}},{"code_sha256_prefix":"643fd0cde93c0eaf","entry":"resolve","repo":"beabevi/policy-learn","repo_kind":"official","path":"config.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"643fd0cde93c0eaf"}},{"code_sha256_prefix":"b2ea0b67cf7e7952","entry":"root_mean_squared_error","repo":"beabevi/policy-learn","repo_kind":"official","path":"utils.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2ea0b67cf7e7952"}},{"code_sha256_prefix":"fecd371d49fabda8","entry":"top_k_gumbel_softmax","repo":"beabevi/policy-learn","repo_kind":"official","path":"utils.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fecd371d49fabda8"}},{"code_sha256_prefix":"edab9c86df31b750","entry":"torch_vrange","repo":"beabevi/policy-learn","repo_kind":"official","path":"extensions.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/extensions.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edab9c86df31b750"}},{"code_sha256_prefix":"6823f6e0df096019","entry":"fqn_import","repo":"beabevi/policy-learn","repo_kind":"official","path":"config.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/config.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":"6823f6e0df096019"}},{"code_sha256_prefix":"08e7484b677b8f03","entry":"setup","repo":"beabevi/policy-learn","repo_kind":"official","path":"utils.py","file_url":"https://github.com/beabevi/policy-learn/blob/HEAD/utils.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":"08e7484b677b8f03"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}