{"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/improving-graph-neural-network","title":"Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling","arxiv_id":"1911.06904","date":"2019-11-15","proceeding":"arXiv 2020 2","authors":["Maxwell Crouse","Ibrahim Abdelaziz","Cristina Cornelio","Veronika Thost","Lingfei Wu","Kenneth Forbus","Achille Fokoue"],"abstract":"Recent advances in the integration of deep learning with automated theorem proving have centered around the representation of logical formulae as inputs to deep learning systems. In particular, there has been a growing interest in adapting structure-aware neural methods to work with the underlying graph representations of logical expressions. While more effective than character and token-level approaches, graph-based methods have often made representational trade-offs that limited their ability to capture key structural properties of their inputs. In this work we propose a novel approach for embedding logical formulae that is designed to overcome the representational limitations of prior approaches. Our architecture works for logics of different expressivity; e.g., first-order and higher-order logic. We evaluate our approach on two standard datasets and show that the proposed architecture achieves state-of-the-art performance on both premise selection and proof step classification.","url_abs":"https://arxiv.org/abs/1911.06904v3","url_pdf":"https://arxiv.org/pdf/1911.06904v3.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":"improving-graph-neural-network","repo_url":"https://github.com/IBM/LogicalFormulaEmbedder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/automated-theorem-proving-on-holstep","task":"Automated Theorem Proving","dataset":"HolStep (Conditional)","model":"MPNN-DagLSTM","rank_in_archive_order":1,"of":5,"metrics":{"Classification Accuracy":"0.916"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.06904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.06904"}},"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/IBM/LogicalFormulaEmbedder","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"6f536216479591ad","entry":"get_ident_pairs","repo":"IBM/LogicalFormulaEmbedder","repo_kind":"listed","path":"code/classifier_modules.py","file_url":"https://github.com/IBM/LogicalFormulaEmbedder/blob/HEAD/code/classifier_modules.py","link_basis":"harvester_set","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":"6f536216479591ad"}},{"code_sha256_prefix":"3c6b77252b5a39ae","entry":"get_item_info","repo":"IBM/LogicalFormulaEmbedder","repo_kind":"listed","path":"code/classifier_modules.py","file_url":"https://github.com/IBM/LogicalFormulaEmbedder/blob/HEAD/code/classifier_modules.py","link_basis":"harvester_set","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":"3c6b77252b5a39ae"}},{"code_sha256_prefix":"75ac87aa01308462","entry":"merge_updates","repo":"IBM/LogicalFormulaEmbedder","repo_kind":"listed","path":"code/classifier_modules.py","file_url":"https://github.com/IBM/LogicalFormulaEmbedder/blob/HEAD/code/classifier_modules.py","link_basis":"harvester_set","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":"75ac87aa01308462"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}