{"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/learning-to-make-predictions-on-graphs-with","title":"Learning to Make Predictions on Graphs with Autoencoders","arxiv_id":"1802.08352","date":"2018-02-23","proceeding":null,"authors":["Phi Vu Tran"],"abstract":"We examine two fundamental tasks associated with graph representation\nlearning: link prediction and semi-supervised node classification. We present a\nnovel autoencoder architecture capable of learning a joint representation of\nboth local graph structure and available node features for the multi-task\nlearning of link prediction and node classification. Our autoencoder\narchitecture is efficiently trained end-to-end in a single learning stage to\nsimultaneously perform link prediction and node classification, whereas\nprevious related methods require multiple training steps that are difficult to\noptimize. We provide a comprehensive empirical evaluation of our models on nine\nbenchmark graph-structured datasets and demonstrate significant improvement\nover related methods for graph representation learning. Reference code and data\nare available at https://github.com/vuptran/graph-representation-learning","url_abs":"http://arxiv.org/abs/1802.08352v2","url_pdf":"http://arxiv.org/pdf/1802.08352v2.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":"learning-to-make-predictions-on-graphs-with","repo_url":"https://github.com/vuptran/graph-representation-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-make-predictions-on-graphs-with","repo_url":"https://github.com/Trent-tangtao/embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-citeseer","task":"Node Classification","dataset":"Citeseer","model":"alpha-LoNGAE","rank_in_archive_order":52,"of":71,"metrics":{"Accuracy":"71.60%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora","task":"Node Classification","dataset":"Cora","model":"alpha-LoNGAE","rank_in_archive_order":68,"of":73,"metrics":{"Accuracy":"78.30%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"alpha-LoNGAE","rank_in_archive_order":46,"of":70,"metrics":{"Accuracy":"79.40%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.08352","atlas_url":"https://app.syntology.ai/?focus=1802.08352","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}