{"url":"/sota/complex-query-answering-on-fb15k","task":{"name":"Complex Query Answering","url":"/task/complex-query-answering","note":null},"dataset":{"name":"FB15k","url":"/dataset/fb15k"},"category":"Graphs","categories":["Graphs","Knowledge Base"],"category_note":null,"description":"This task is concerned with answering complex queries over incomplete knowledge graphs. In the most simple case, the task is reduced to link prediction: a 1-hop query for predicting the existence of an edge between a pair of nodes. Complex queries are concerned with other structures between nodes, such as 2-hop and 3-paths, and intersecting paths with intermediate variables.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["MRR 1p","MRR 2i","MRR 2p","MRR 2u","MRR 3i","MRR 3p","MRR ip","MRR pi","MRR up","Hits@3 1p","Hits@3 2i","Hits@3 2p","Hits@3 2u","Hits@3 3i","Hits@3 3p","Hits@3 ip","Hits@3 pi","Hits@3 up"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"MRR 1p":"higher","MRR 2i":"higher","MRR 2p":"higher","MRR 2u":"higher","MRR 3i":"higher","MRR 3p":"higher","MRR ip":"higher","MRR pi":"higher","MRR up":"higher","Hits@3 1p":null,"Hits@3 2i":null,"Hits@3 2p":null,"Hits@3 2u":null,"Hits@3 3i":null,"Hits@3 3p":null,"Hits@3 ip":null,"Hits@3 pi":null,"Hits@3 up":null}},"counts":{"rows":9,"rows_with_code":8,"rows_with_paper_page":9,"rows_dated":9,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"QTO","metrics":{"MRR 1p":"0.895","MRR 2i":"0.803","MRR 2p":"0.674","MRR 2u":"0.767","MRR 3i":"0.836","MRR 3p":"0.588","MRR ip":"0.740","MRR pi":"0.752","MRR up":"0.613"},"uses_additional_data":false,"paper_date":"2022-12-19","paper":"/paper/answering-complex-logical-queries-on","paper_url":"https://arxiv.org/abs/2212.09567v3","paper_title":"Answering Complex Logical Queries on Knowledge Graphs via Query Computation Tree Optimization","code":"https://github.com/bys0318/qto","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":6,"n_samples":7,"n_pointer_only_licence":7}},{"rank_in_archive_order":2,"model":"CQD","metrics":{"MRR 1p":"0.892","MRR 2i":"0.771","MRR 2p":"0.653","MRR 2u":"0.723","MRR 3i":"0.806","MRR ip":"0.716"},"uses_additional_data":false,"paper_date":"2020-11-06","paper":"/paper/complex-query-answering-with-neural-link-1","paper_url":"https://arxiv.org/abs/2011.03459v4","paper_title":"Complex Query Answering with Neural Link Predictors","code":"https://github.com/uclnlp/cqd","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"CQDA","metrics":{"MRR 1p":"0.892","MRR 2i":"0.761","MRR 2p":"0.645","MRR 2u":"0.684","MRR 3i":"0.794","MRR 3p":"0.579","MRR ip":"0.706","MRR pi":"0.701","MRR up":"0.579"},"uses_additional_data":false,"paper_date":"2023-01-29","paper":"/paper/adapting-neural-link-predictors-for-complex","paper_url":"https://arxiv.org/abs/2301.12313v3","paper_title":"Adapting Neural Link Predictors for Data-Efficient Complex Query Answering","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"GNN-QE","metrics":{"MRR 1p":"0.885","MRR 2i":"0.797","MRR 2p":"0.693","MRR 2u":"0.741","MRR 3i":"0.835","MRR 3p":"0.587","MRR ip":"0.704","MRR pi":"0.699","MRR up":"0.610"},"uses_additional_data":false,"paper_date":"2022-05-16","paper":"/paper/neural-symbolic-models-for-logical-queries-on","paper_url":"https://arxiv.org/abs/2205.10128v2","paper_title":"Neural-Symbolic Models for Logical Queries on Knowledge Graphs","code":"https://github.com/DeepGraphLearning/GNN-QE","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"Q2B","metrics":{"MRR 1p":"0.68","MRR 2i":"0.551","MRR 2p":"0.21","MRR 2u":"0.351","MRR 3i":"0.665","MRR 3p":"0.142","MRR ip":"0.261","MRR pi":"0.394","MRR up":"0.167"},"uses_additional_data":false,"paper_date":"2020-02-14","paper":"/paper/query2box-reasoning-over-knowledge-graphs-in-1","paper_url":"https://arxiv.org/abs/2002.05969v2","paper_title":"Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings","code":"https://github.com/snap-stanford/KGReasoning","n_code_links":9,"syntology":{"n_ran":30,"n_unverified":11,"n_samples":41,"n_pointer_only_licence":2}},{"rank_in_archive_order":6,"model":"BetaE","metrics":{"MRR 1p":"0.651","MRR 2i":"0.558","MRR 2p":"0.257","MRR 2u":"0.401","MRR 3i":"0.665","MRR 3p":"0.247","MRR ip":"0.281","MRR pi":"0.439","MRR up":"0.252"},"uses_additional_data":false,"paper_date":"2020-10-22","paper":"/paper/beta-embeddings-for-multi-hop-logical","paper_url":"https://arxiv.org/abs/2010.11465v1","paper_title":"Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs","code":"https://github.com/snap-stanford/KGReasoning","n_code_links":9,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":1}},{"rank_in_archive_order":7,"model":"GQE","metrics":{"MRR 1p":"0.546","MRR 2i":"0.397","MRR 2p":"0.153","MRR 2u":"0.221","MRR 3i":"0.514","MRR 3p":"0.108","MRR ip":"0.191","MRR pi":"0.276","MRR up":"0.116"},"uses_additional_data":false,"paper_date":"2018-06-05","paper":"/paper/embedding-logical-queries-on-knowledge-graphs","paper_url":"https://arxiv.org/abs/1806.01445v4","paper_title":"Embedding Logical Queries on Knowledge Graphs","code":"https://github.com/snap-stanford/KGReasoning","n_code_links":12,"syntology":{"n_ran":4,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":8,"model":"CQD-Beam","metrics":{"Hits@3 1p":"0.918","Hits@3 2i":"0.796","Hits@3 2p":"0.779","Hits@3 2u":"0.839","Hits@3 3i":"0.837","Hits@3 3p":"0.577","Hits@3 ip":"0.375","Hits@3 pi":"0.658","Hits@3 up":"0.345"},"uses_additional_data":false,"paper_date":"2020-11-06","paper":"/paper/complex-query-answering-with-neural-link-1","paper_url":"https://arxiv.org/abs/2011.03459v4","paper_title":"Complex Query Answering with Neural Link Predictors","code":"https://github.com/uclnlp/cqd","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}},{"rank_in_archive_order":9,"model":"CQD-CO","metrics":{"Hits@3 1p":"0.918","Hits@3 2i":"0.796","Hits@3 2p":"0.454","Hits@3 2u":"0.816","Hits@3 3i":"0.837","Hits@3 3p":"0.191","Hits@3 ip":"0.336","Hits@3 pi":"0.513","Hits@3 up":"0.319"},"uses_additional_data":false,"paper_date":"2020-11-06","paper":"/paper/complex-query-answering-with-neural-link-1","paper_url":"https://arxiv.org/abs/2011.03459v4","paper_title":"Complex Query Answering with Neural Link Predictors","code":"https://github.com/uclnlp/cqd","n_code_links":5,"syntology":{"n_ran":5,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":4}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,885 of the 9,623 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":8,"rows_with_any_sample_ran":8,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":50,"n_unverified":27,"n_samples":77,"n_pointer_only_licence":15,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":60,"n_unverified":31,"n_samples":91,"n_pointer_only_licence":23,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}