{"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/how-powerful-is-graph-convolution-for","title":"How Powerful is Graph Convolution for Recommendation?","arxiv_id":"2108.07567","date":"2021-08-17","proceeding":null,"authors":["Yifei Shen","Yongji Wu","Yao Zhang","Caihua Shan","Jun Zhang","Khaled B. Letaief","Dongsheng Li"],"abstract":"Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms for collaborative filtering (CF). Nevertheless, the theoretical underpinnings of their empirical successes remain elusive. In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing. By identifying the critical role of smoothness, a key concept in graph signal processing, we develop a unified graph convolution-based framework for CF. We prove that many existing CF methods are special cases of this framework, including the neighborhood-based methods, low-rank matrix factorization, linear auto-encoders, and LightGCN, corresponding to different low-pass filters. Based on our framework, we then present a simple and computationally efficient CF baseline, which we shall refer to as Graph Filter based Collaborative Filtering (GF-CF). Given an implicit feedback matrix, GF-CF can be obtained in a closed form instead of expensive training with back-propagation. Experiments will show that GF-CF achieves competitive or better performance against deep learning-based methods on three well-known datasets, notably with a $70\\%$ performance gain over LightGCN on the Amazon-book dataset.","url_abs":"https://arxiv.org/abs/2108.07567v1","url_pdf":"https://arxiv.org/pdf/2108.07567v1.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":"how-powerful-is-graph-convolution-for","repo_url":"https://github.com/yshenaw/GF_CF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"}],"methods":[{"method_slug":"lightgcn","method_name":"LightGCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-gowalla","task":"Collaborative Filtering","dataset":"Gowalla","model":"GF-CF","rank_in_archive_order":9,"of":11,"metrics":{"NDCG@20":"0.1518","Recall@20":"0.1849"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.07567","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}