{"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/tensor-decompositions-for-temporal-knowledge-1","title":"Tensor Decompositions for temporal knowledge base completion","arxiv_id":"2004.04926","date":"2020-04-10","proceeding":"ICLR 2020 1","authors":["Timothée Lacroix","Guillaume Obozinski","Nicolas Usunier"],"abstract":"Most algorithms for representation learning and link prediction in relational data have been designed for static data. However, the data they are applied to usually evolves with time, such as friend graphs in social networks or user interactions with items in recommender systems. This is also the case for knowledge bases, which contain facts such as (US, has president, B. Obama, [2009-2017]) that are valid only at certain points in time. For the problem of link prediction under temporal constraints, i.e., answering queries such as (US, has president, ?, 2012), we propose a solution inspired by the canonical decomposition of tensors of order 4. We introduce new regularization schemes and present an extension of ComplEx (Trouillon et al., 2016) that achieves state-of-the-art performance. Additionally, we propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.","url_abs":"https://arxiv.org/abs/2004.04926v1","url_pdf":"https://arxiv.org/pdf/2004.04926v1.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":"tensor-decompositions-for-temporal-knowledge-1","repo_url":"https://github.com/facebookresearch/tkbc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"tensor-decompositions-for-temporal-knowledge-1","repo_url":"https://github.com/apoorvumang/CronKGQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-base-completion","task_name":"Knowledge Base Completion"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-icews05-15-1","task":"Link Prediction","dataset":"ICEWS05-15","model":"TNTComplEx (x10)","rank_in_archive_order":3,"of":16,"metrics":{"MRR":"0.67"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-icews05-15-1","task":"Link Prediction","dataset":"ICEWS05-15","model":"TNTComplEx","rank_in_archive_order":6,"of":16,"metrics":{"MRR":"0.60"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-icews14-1","task":"Link Prediction","dataset":"ICEWS14","model":"TNTComplEx (x10)","rank_in_archive_order":3,"of":16,"metrics":{"MRR":"0.62"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-icews14-1","task":"Link Prediction","dataset":"ICEWS14","model":"TNTComplEx","rank_in_archive_order":6,"of":16,"metrics":{"MRR":"0.56"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yago15k-1","task":"Link Prediction","dataset":"YAGO15k","model":"TNTComplEx (x10)","rank_in_archive_order":1,"of":2,"metrics":{"MRR":"0.37"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yago15k-1","task":"Link Prediction","dataset":"YAGO15k","model":"TNTComplEx","rank_in_archive_order":2,"of":2,"metrics":{"MRR":"0.35"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.04926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04926"}},"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/apoorvumang/CronKGQA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/tkbc","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"58ce62d38fb12832","entry":"get_be","repo":"facebookresearch/tkbc","repo_kind":"official","path":"tkbc/process_wikidata.py","file_url":"https://github.com/facebookresearch/tkbc/blob/HEAD/tkbc/process_wikidata.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"58ce62d38fb12832"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}