{"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/graph-representation-learning-beyond-node-and","title":"Graph Representation Learning Beyond Node and Homophily","arxiv_id":"2203.01564","date":"2022-03-03","proceeding":null,"authors":["You Li","Bei Lin","Binli Luo","Ning Gui"],"abstract":"Unsupervised graph representation learning aims to distill various graph information into a downstream task-agnostic dense vector embedding. However, existing graph representation learning approaches are designed mainly under the node homophily assumption: connected nodes tend to have similar labels and optimize performance on node-centric downstream tasks. Their design is apparently against the task-agnostic principle and generally suffers poor performance in tasks, e.g., edge classification, that demands feature signals beyond the node-view and homophily assumption. To condense different feature signals into the embeddings, this paper proposes PairE, a novel unsupervised graph embedding method using two paired nodes as the basic unit of embedding to retain the high-frequency signals between nodes to support node-related and edge-related tasks. Accordingly, a multi-self-supervised autoencoder is designed to fulfill two pretext tasks: one retains the high-frequency signal better, and another enhances the representation of commonality. Our extensive experiments on a diversity of benchmark datasets clearly show that PairE outperforms the unsupervised state-of-the-art baselines, with up to 101.1\\% relative improvement on the edge classification tasks that rely on both the high and low-frequency signals in the pair and up to 82.5\\% relative performance gain on the node classification tasks.","url_abs":"https://arxiv.org/abs/2203.01564v1","url_pdf":"https://arxiv.org/pdf/2203.01564v1.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":"graph-representation-learning-beyond-node-and","repo_url":"https://github.com/syvail/PairE-Graph-Representation-Learning-Beyond-Node-and-Homophily","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"edge-classification","task_name":"Edge Classification"},{"task_slug":"graph-embedding","task_name":"Graph Embedding"},{"task_slug":"graph-representation-learning","task_name":"Graph Representation Learning"},{"task_slug":"node-classification","task_name":"Node Classification"},{"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":"PairE","rank_in_archive_order":21,"of":71,"metrics":{"Accuracy":"75.53"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cora-fixed-20-node-per","task":"Node Classification","dataset":"Cora: fixed 20 node per class","model":"PairE","rank_in_archive_order":9,"of":9,"metrics":{"Micro F1":"75.12"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-dblp","task":"Node Classification","dataset":"DBLP","model":"PairE","rank_in_archive_order":5,"of":6,"metrics":{"Micro F1":"80.58"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-deezer-romania","task":"Node Classification","dataset":"Deezer Romania","model":"PairE","rank_in_archive_order":1,"of":2,"metrics":{"Micro-F1":"0.68"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ppi","task":"Node Classification","dataset":"PPI","model":"PairE","rank_in_archive_order":22,"of":24,"metrics":{"Micro F1":"94.83"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-pubmed","task":"Node Classification","dataset":"Pubmed","model":"PairE","rank_in_archive_order":67,"of":70,"metrics":{"F1":"88.57"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}