{"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/gaussian-embedding-of-large-scale-attributed","title":"Gaussian Embedding of Large-scale Attributed Graphs","arxiv_id":"1912.00536","date":"2019-12-02","proceeding":null,"authors":["Bhagya Hettige","Yuan-Fang Li","Weiqing Wang","Wray Buntine"],"abstract":"Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner. GLACE effectively models uncertainty through Gaussian embeddings, and supports inductive inference of new nodes based on their attributes. In our comprehensive experiments, we evaluate GLACE on real-world graphs, and the results demonstrate that GLACE significantly outperforms state-of-the-art embedding methods on multiple graph analysis tasks.","url_abs":"https://arxiv.org/abs/1912.00536v1","url_pdf":"https://arxiv.org/pdf/1912.00536v1.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":"gaussian-embedding-of-large-scale-attributed","repo_url":"https://github.com/bhagya-hettige/GLACE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-acm","task":"Link Prediction","dataset":"ACM","model":"GLACE","rank_in_archive_order":1,"of":1,"metrics":{"AP":"98.24","AUC":"98.34"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-citeseer-nonstandard","task":"Link Prediction","dataset":"Citeseer (nonstandard variant)","model":"GLACE","rank_in_archive_order":1,"of":1,"metrics":{"AP":"98.37","AUC":"98.43"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-cora-nonstandard-variant","task":"Link Prediction","dataset":"Cora (nonstandard variant)","model":"GLACE","rank_in_archive_order":1,"of":1,"metrics":{"AP":"98.52","AUC":"98.6"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-dblp","task":"Link Prediction","dataset":"DBLP","model":"GLACE","rank_in_archive_order":1,"of":3,"metrics":{"AP":"98.4","AUC":"98.55"},"uses_additional_data":false},{"leaderboard":"/sota/link-prediction-on-pubmed-nonstandard-variant","task":"Link Prediction","dataset":"Pubmed (nonstandard variant)","model":"GLACE","rank_in_archive_order":1,"of":1,"metrics":{"AP":"97.49","AUC":"97.82"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}