{"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/neural-methods-for-logical-reasoning-over-1","title":"Neural Methods for Logical Reasoning Over Knowledge Graphs","arxiv_id":"2209.14464","date":"2022-09-28","proceeding":"ICLR 2022 4","authors":["Alfonso Amayuelas","Shuai Zhang","Susie Xi Rao","Ce Zhang"],"abstract":"Reasoning is a fundamental problem for computers and deeply studied in Artificial Intelligence. In this paper, we specifically focus on answering multi-hop logical queries on Knowledge Graphs (KGs). This is a complicated task because, in real-world scenarios, the graphs tend to be large and incomplete. Most previous works have been unable to create models that accept full First-Order Logical (FOL) queries, which include negative queries, and have only been able to process a limited set of query structures. Additionally, most methods present logic operators that can only perform the logical operation they are made for. We introduce a set of models that use Neural Networks to create one-point vector embeddings to answer the queries. The versatility of neural networks allows the framework to handle FOL queries with Conjunction ($\\wedge$), Disjunction ($\\vee$) and Negation ($\\neg$) operators. We demonstrate experimentally the performance of our model through extensive experimentation on well-known benchmarking datasets. Besides having more versatile operators, the models achieve a 10\\% relative increase over the best performing state of the art and more than 30\\% over the original method based on single-point vector embeddings.","url_abs":"https://arxiv.org/abs/2209.14464v1","url_pdf":"https://arxiv.org/pdf/2209.14464v1.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":"neural-methods-for-logical-reasoning-over-1","repo_url":"https://github.com/amayuelas/NNKGReasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"negation","task_name":"Negation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.14464","atlas_url":"https://app.syntology.ai/?focus=2209.14464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14464"}},"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/amayuelas/NNKGReasoning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"f44985272d18127a","entry":"Identity","repo":"amayuelas/NNKGReasoning","repo_kind":"official","path":"models/baselines.py","file_url":"https://github.com/amayuelas/NNKGReasoning/blob/HEAD/models/baselines.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f44985272d18127a"}},{"code_sha256_prefix":"08bc9653c017dfb5","entry":"eval_tuple","repo":"amayuelas/NNKGReasoning","repo_kind":"official","path":"util.py","file_url":"https://github.com/amayuelas/NNKGReasoning/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08bc9653c017dfb5"}},{"code_sha256_prefix":"8c314b5b308ab1ad","entry":"list2tuple","repo":"amayuelas/NNKGReasoning","repo_kind":"official","path":"util.py","file_url":"https://github.com/amayuelas/NNKGReasoning/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8c314b5b308ab1ad"}},{"code_sha256_prefix":"bbd072fbd86e1541","entry":"tuple2list","repo":"amayuelas/NNKGReasoning","repo_kind":"official","path":"util.py","file_url":"https://github.com/amayuelas/NNKGReasoning/blob/HEAD/util.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbd072fbd86e1541"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}