{"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/binarized-knowledge-graph-embeddings","title":"Binarized Knowledge Graph Embeddings","arxiv_id":"1902.02970","date":"2019-02-08","proceeding":null,"authors":["Koki Kishimoto","Katsuhiko Hayashi","Genki Akai","Masashi Shimbo","Kazunori Komatani"],"abstract":"Tensor factorization has become an increasingly popular approach to knowledge\ngraph completion(KGC), which is the task of automatically predicting missing\nfacts in a knowledge graph. However, even with a simple model like\nCANDECOMP/PARAFAC(CP) tensor decomposition, KGC on existing knowledge graphs is\nimpractical in resource-limited environments, as a large amount of memory is\nrequired to store parameters represented as 32-bit or 64-bit floating point\nnumbers. This limitation is expected to become more stringent as existing\nknowledge graphs, which are already huge, keep steadily growing in scale. To\nreduce the memory requirement, we present a method for binarizing the\nparameters of the CP tensor decomposition by introducing a quantization\nfunction to the optimization problem. This method replaces floating\npoint-valued parameters with binary ones after training, which drastically\nreduces the model size at run time. We investigate the trade-off between the\nquality and size of tensor factorization models for several KGC benchmark\ndatasets. In our experiments, the proposed method successfully reduced the\nmodel size by more than an order of magnitude while maintaining the task\nperformance. Moreover, a fast score computation technique can be developed with\nbitwise operations.","url_abs":"http://arxiv.org/abs/1902.02970v1","url_pdf":"http://arxiv.org/pdf/1902.02970v1.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":"binarized-knowledge-graph-embeddings","repo_url":"https://github.com/KokiKishimoto/cp_decomposition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"binarized-knowledge-graph-embeddings","repo_url":"https://github.com/KokiKishimoto/cp_decomposition_alpha","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"knowledge-graph-completion","task_name":"Knowledge Graph Completion"},{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}