{"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/pytorch-biggraph-a-large-scale-graph","title":"PyTorch-BigGraph: A Large-scale Graph Embedding System","arxiv_id":"1903.12287","date":"2019-03-28","proceeding":null,"authors":["Adam Lerer","Ledell Wu","Jiajun Shen","Timothee Lacroix","Luca Wehrstedt","Abhijit Bose","Alex Peysakhovich"],"abstract":"Graph embedding methods produce unsupervised node features from graphs that\ncan then be used for a variety of machine learning tasks. Modern graphs,\nparticularly in industrial applications, contain billions of nodes and\ntrillions of edges, which exceeds the capability of existing embedding systems.\nWe present PyTorch-BigGraph (PBG), an embedding system that incorporates\nseveral modifications to traditional multi-relation embedding systems that\nallow it to scale to graphs with billions of nodes and trillions of edges. PBG\nuses graph partitioning to train arbitrarily large embeddings on either a\nsingle machine or in a distributed environment. We demonstrate comparable\nperformance with existing embedding systems on common benchmarks, while\nallowing for scaling to arbitrarily large graphs and parallelization on\nmultiple machines. We train and evaluate embeddings on several large social\nnetwork graphs as well as the full Freebase dataset, which contains over 100\nmillion nodes and 2 billion edges.","url_abs":"http://arxiv.org/abs/1903.12287v3","url_pdf":"http://arxiv.org/pdf/1903.12287v3.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":"pytorch-biggraph-a-large-scale-graph","repo_url":"https://github.com/facebookresearch/PyTorch-BigGraph","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"graph-partitioning","task_name":"graph partitioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-fb15k-1","task":"Link Prediction","dataset":"FB15k","model":"PyTorch BigGraph (ComplEx)","rank_in_archive_order":5,"of":10,"metrics":{"Hits@10":"0.872","MRR":"0.79","MRR raw":"0.242"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-livejournal","task":"Link Prediction","dataset":"LiveJournal","model":"PBG (1 partition)","rank_in_archive_order":1,"of":2,"metrics":{"Hits@10":"0.857","MR":"245.9"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-livejournal","task":"Link Prediction","dataset":"LiveJournal","model":"PyTorch BigGraph","rank_in_archive_order":2,"of":2,"metrics":{"MRR":"0.749"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-youtube","task":"Link Prediction","dataset":"YouTube","model":"PyTorch BigGraph","rank_in_archive_order":2,"of":2,"metrics":{"Macro F1":"40.9","Micro F1":"48"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.12287","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}