{"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/hypernetwork-knowledge-graph-embeddings","title":"Hypernetwork Knowledge Graph Embeddings","arxiv_id":"1808.07018","date":"2018-08-21","proceeding":null,"authors":["Ivana Balažević","Carl Allen","Timothy M. Hospedales"],"abstract":"Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction. A recent state-of-the-art approach to link prediction, ConvE, implements a convolutional neural network to extract features from concatenated subject and relation vectors. Whilst results are impressive, the method is unintuitive and poorly understood. We propose a hypernetwork architecture that generates simplified relation-specific convolutional filters that (i) outperforms ConvE and all previous approaches across standard datasets; and (ii) can be framed as tensor factorization and thus set within a well established family of factorization models for link prediction. We thus demonstrate that convolution simply offers a convenient computational means of introducing sparsity and parameter tying to find an effective trade-off between non-linear expressiveness and the number of parameters to learn.","url_abs":"https://arxiv.org/abs/1808.07018v5","url_pdf":"https://arxiv.org/pdf/1808.07018v5.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":"hypernetwork-knowledge-graph-embeddings","repo_url":"https://github.com/ibalazevic/HypER","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":null,"task_name":"Relation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"hypernetwork","method_name":"HyperNetwork"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k","task":"Link Prediction","dataset":"FB15k","model":"HypER","rank_in_archive_order":10,"of":23,"metrics":{"Hits@1":"0.734","Hits@10":"0.885","Hits@3":"0.829","MRR":"0.790"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-fb15k-237","task":"Link Prediction","dataset":"FB15k-237","model":"HypER","rank_in_archive_order":34,"of":75,"metrics":{"Hits@1":"0.252","Hits@10":"0.520","Hits@3":"0.376","MRR":"0.341"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"HypER","rank_in_archive_order":11,"of":37,"metrics":{"Hits@1":"0.947","Hits@10":"0.958","Hits@3":"0.955","MRR":"0.951"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-wn18rr","task":"Link Prediction","dataset":"WN18RR","model":"HypER","rank_in_archive_order":63,"of":75,"metrics":{"Hits@1":"0.436","Hits@10":"0.522","Hits@3":"0.477","MR":"5796","MRR":"0.465"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.07018","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}