{"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/simple-embedding-for-link-prediction-in","title":"SimplE Embedding for Link Prediction in Knowledge Graphs","arxiv_id":"1802.04868","date":"2018-02-13","proceeding":"NeurIPS 2018 12","authors":["Seyed Mehran Kazemi","David Poole"],"abstract":"Knowledge graphs contain knowledge about the world and provide a structured\nrepresentation of this knowledge. Current knowledge graphs contain only a small\nsubset of what is true in the world. Link prediction approaches aim at\npredicting new links for a knowledge graph given the existing links among the\nentities. Tensor factorization approaches have proved promising for such link\nprediction problems. Proposed in 1927, Canonical Polyadic (CP) decomposition is\namong the first tensor factorization approaches. CP generally performs poorly\nfor link prediction as it learns two independent embedding vectors for each\nentity, whereas they are really tied. We present a simple enhancement of CP\n(which we call SimplE) to allow the two embeddings of each entity to be learned\ndependently. The complexity of SimplE grows linearly with the size of\nembeddings. The embeddings learned through SimplE are interpretable, and\ncertain types of background knowledge can be incorporated into these embeddings\nthrough weight tying. We prove SimplE is fully expressive and derive a bound on\nthe size of its embeddings for full expressivity. We show empirically that,\ndespite its simplicity, SimplE outperforms several state-of-the-art tensor\nfactorization techniques. SimplE's code is available on GitHub at\nhttps://github.com/Mehran-k/SimplE.","url_abs":"http://arxiv.org/abs/1802.04868v2","url_pdf":"http://arxiv.org/pdf/1802.04868v2.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":"simple-embedding-for-link-prediction-in","repo_url":"https://github.com/Mehran-k/SimplE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"simple-embedding-for-link-prediction-in","repo_url":"https://github.com/davendw49/gakg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k","task":"Link Prediction","dataset":"FB15k","model":"SimplE","rank_in_archive_order":16,"of":23,"metrics":{"Hits@1":"0.660","Hits@10":"0.838","Hits@3":"0.773","MRR":"0.727"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"SimplE","rank_in_archive_order":25,"of":37,"metrics":{"Hits@1":"0.939","Hits@10":"0.947","Hits@3":"0.944","MRR":"0.942"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.04868","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}