{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/adapting-neural-link-predictors-for-complex","title":"Adapting Neural Link Predictors for Data-Efficient Complex Query Answering","arxiv_id":"2301.12313","date":"2023-01-29","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Answering complex queries on incomplete knowledge graphs is a challenging task where a model needs to answer complex logical queries in the presence of missing knowledge. Prior work in the literature has proposed to address this problem by designing architectures trained end-to-end for the complex query answering task with a reasoning process that is hard to interpret while requiring data and resource-intensive training. Other lines of research have proposed re-using simple neural link predictors to answer complex queries, reducing the amount of training data by orders of magnitude while providing interpretable answers. The neural link predictor used in such approaches is not explicitly optimised for the complex query answering task, implying that its scores are not calibrated to interact together. We propose to address these problems via CQD$^{\\mathcal{A}}$, a parameter-efficient score \\emph{adaptation} model optimised to re-calibrate neural link prediction scores for the complex query answering task. While the neural link predictor is frozen, the adaptation component -- which only increases the number of model parameters by $0.03\\%$ -- is trained on the downstream complex query answering task. Furthermore, the calibration component enables us to support reasoning over queries that include atomic negations, which was previously impossible with link predictors. In our experiments, CQD$^{\\mathcal{A}}$ produces significantly more accurate results than current state-of-the-art methods, improving from $34.4$ to $35.1$ Mean Reciprocal Rank values averaged across all datasets and query types while using $\\leq 30\\%$ of the available training query types. We further show that CQD$^{\\mathcal{A}}$ is data-efficient, achieving competitive results with only $1\\%$ of the training complex queries, and robust in out-of-domain evaluations.","url_abs":"https://arxiv.org/abs/2301.12313v3","url_pdf":"https://arxiv.org/pdf/2301.12313v3.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":[],"tasks":[{"task_slug":"complex-query-answering","task_name":"Complex Query Answering"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/complex-query-answering-on-fb15k","task":"Complex Query Answering","dataset":"FB15k","model":"CQDA","rank_in_archive_order":3,"of":9,"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},{"leaderboard":"/sota/complex-query-answering-on-fb15k-237","task":"Complex Query Answering","dataset":"FB15k-237","model":"CQDA","rank_in_archive_order":2,"of":9,"metrics":{"MRR 1p":"0.467","MRR 2i":"0.345","MRR 2p":"0.136","MRR 2u":"0.176","MRR 3i":"0.483","MRR 3p":"0.114","MRR ip":"0.209","MRR pi":"0.274","MRR up":"0.114"},"uses_additional_data":false},{"leaderboard":"/sota/complex-query-answering-on-nell-995","task":"Complex Query Answering","dataset":"NELL-995","model":"CQDA","rank_in_archive_order":3,"of":6,"metrics":{"MRR 1p":"0.604","MRR 2i":"0.434","MRR 2p":"0.229","MRR 2u":"0.200","MRR 3i":"0.526","MRR 3p":"0.167","MRR ip":"0.264","MRR pi":"0.321","MRR up":"0.170"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.12313","atlas_url":"https://app.syntology.ai/?focus=2301.12313","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2301.12313"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2301.12313\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2301.12313"},"call":"get_concepts_for_paper(arxiv_id=\"2301.12313\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7559cad1464deed549bb243196768e3bac047d8a145670cf37654bb9d32357d3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}