{"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/simple-truncated-svd-based-model-for-node","title":"Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs","arxiv_id":"2106.12807","date":"2021-06-24","proceeding":null,"authors":["Vijay Lingam","Rahul Ragesh","Arun Iyer","Sundararajan Sellamanickam"],"abstract":"Graph Neural Networks (GNNs) have shown excellent performance on graphs that exhibit strong homophily with respect to the node labels i.e. connected nodes have same labels. However, they perform poorly on heterophilic graphs. Recent approaches have typically modified aggregation schemes, designed adaptive graph filters, etc. to address this limitation. In spite of this, the performance on heterophilic graphs can still be poor. We propose a simple alternative method that exploits Truncated Singular Value Decomposition (TSVD) of topological structure and node features. Our approach achieves up to ~30% improvement in performance over state-of-the-art methods on heterophilic graphs. This work is an early investigation into methods that differ from aggregation based approaches. Our experimental results suggest that it might be important to explore other alternatives to aggregation methods for heterophilic setting.","url_abs":"https://arxiv.org/abs/2106.12807v1","url_pdf":"https://arxiv.org/pdf/2106.12807v1.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":[],"tasks":[{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-classification-on-actor","task":"Node Classification","dataset":"Actor","model":"HLP Concat","rank_in_archive_order":49,"of":62,"metrics":{"Accuracy":"34.59 ± 1.32"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-chameleon","task":"Node Classification","dataset":"Chameleon","model":"HLP Concat","rank_in_archive_order":7,"of":61,"metrics":{"Accuracy":"77.48±0.80"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-cornell","task":"Node Classification","dataset":"Cornell","model":"HLP Concat","rank_in_archive_order":28,"of":60,"metrics":{"Accuracy":"84.05±4.67"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-crocodile","task":"Node Classification","dataset":"Crocodile","model":"HLP Concat","rank_in_archive_order":2,"of":2,"metrics":{"Accuracy":"55.87±1.25"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-squirrel","task":"Node Classification","dataset":"Squirrel","model":"HLP Concat","rank_in_archive_order":4,"of":59,"metrics":{"Accuracy":"74.17±1.83"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-texas","task":"Node Classification","dataset":"Texas","model":"HLP Concat","rank_in_archive_order":14,"of":62,"metrics":{"Accuracy":"87.57 ± 5.44"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-wisconsin","task":"Node Classification","dataset":"Wisconsin","model":"HLP Concat","rank_in_archive_order":35,"of":63,"metrics":{"Accuracy":"86.67±4.22"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.12807","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}