{"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/multi-partition-embedding-interaction-with","title":"Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion","arxiv_id":"2006.16365","date":"2020-06-29","proceeding":null,"authors":["Hung Nghiep Tran","Atsuhiro Takasu"],"abstract":"Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between these whole embeddings, potentially making the model excessively expensive or requiring specially designed interaction mechanisms. In this work, we propose the multi-partition embedding interaction (MEI) model with block term format to systematically address this problem. MEI divides each embedding into a multi-partition vector to efficiently restrict the interactions. Each local interaction is modeled with the Tucker tensor format and the full interaction is modeled with the block term tensor format, enabling MEI to control the trade-off between expressiveness and computational cost, learn the interaction mechanisms from data automatically, and achieve state-of-the-art performance on the link prediction task. In addition, we theoretically study the parameter efficiency problem and derive a simple empirically verified criterion for optimal parameter trade-off. We also apply the framework of MEI to provide a new generalized explanation for several specially designed interaction mechanisms in previous models. The source code is released at https://github.com/tranhungnghiep/MEI-KGE.","url_abs":"https://arxiv.org/abs/2006.16365v2","url_pdf":"https://arxiv.org/pdf/2006.16365v2.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":"multi-partition-embedding-interaction-with","repo_url":"https://github.com/tranhungnghiep/MEI-KGE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-partition-embedding-interaction-with","repo_url":"https://github.com/tranhungnghiep/AnalyzeKGE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"knowledge-graph-embedding","task_name":"Knowledge Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"mei","method_name":"MEI"},{"method_slug":"tucker","method_name":"TuckER"}],"datasets_introduced":[],"methods_introduced":[{"slug":"mei","name":"MEI","full_name":"Multi-partition Embedding Interaction"}],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-1","task":"Link Prediction","dataset":"FB15k","model":"MEI (small)","rank_in_archive_order":3,"of":10,"metrics":{"Hits@1":"0.757","Hits@10":"0.878","Hits@3":"0.823","MRR":"0.800"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k","task":"Link Prediction","dataset":"FB15k","model":"MEI-BTD","rank_in_archive_order":5,"of":23,"metrics":{"Hits@1":"0.754","Hits@10":"0.893","Hits@3":"0.843","MRR":"0.806"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"MEI","rank_in_archive_order":13,"of":75,"metrics":{"Hits@1":"0.271","Hits@10":"0.552","Hits@3":"0.402","MRR":"0.365"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-kg20c","task":"Link Prediction","dataset":"KG20C","model":"MEI (small)","rank_in_archive_order":1,"of":3,"metrics":{"Hits@1":"0.157","Hits@10":"0.368","Hits@3":"0.258","MRR":"0.230"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"MEI (small)","rank_in_archive_order":5,"of":37,"metrics":{"Hits@1":"0.946","Hits@10":"0.960","Hits@3":"0.953","MRR":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"MEI-BTD","rank_in_archive_order":13,"of":37,"metrics":{"Hits@1":"0.946","Hits@10":"0.957","Hits@3":"0.952","MRR":"0.950"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"MEI","rank_in_archive_order":52,"of":75,"metrics":{"Hits@1":"0.444","Hits@10":"0.551","Hits@3":"0.496","MRR":"0.481"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-yago3-10","task":"Link Prediction","dataset":"YAGO3-10","model":"MEI","rank_in_archive_order":4,"of":18,"metrics":{"Hits@1":"0.505","Hits@10":"0.709","Hits@3":"0.622","MR":"756","MRR":"0.578"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.16365","atlas_url":"https://app.syntology.ai/?focus=2006.16365","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":"2006.16365"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2006.16365\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2006.16365"},"call":"get_concepts_for_paper(arxiv_id=\"2006.16365\")"}],"by_repo":[{"repo":"tranhungnghiep/MEI-KGE","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tranhungnghiep/AnalyzeKGE","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"34ef41cdc41afd5ef538883bdae0908293d6d023fc6817c26b96133ba2e3d8b9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}