{"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/svd-gcn-a-simplified-graph-convolution","title":"SVD-GCN: A Simplified Graph Convolution Paradigm for Recommendation","arxiv_id":"2208.12689","date":"2022-08-26","proceeding":null,"authors":["Shaowen Peng","Kazunari Sugiyama","Tsunenori Mine"],"abstract":"With the tremendous success of Graph Convolutional Networks (GCNs), they have been widely applied to recommender systems and have shown promising performance. However, most GCN-based methods rigorously stick to a common GCN learning paradigm and suffer from two limitations: (1) the limited scalability due to the high computational cost and slow training convergence; (2) the notorious over-smoothing issue which reduces performance as stacking graph convolution layers. We argue that the above limitations are due to the lack of a deep understanding of GCN-based methods. To this end, we first investigate what design makes GCN effective for recommendation. By simplifying LightGCN, we show the close connection between GCN-based and low-rank methods such as Singular Value Decomposition (SVD) and Matrix Factorization (MF), where stacking graph convolution layers is to learn a low-rank representation by emphasizing (suppressing) components with larger (smaller) singular values. Based on this observation, we replace the core design of GCN-based methods with a flexible truncated SVD and propose a simplified GCN learning paradigm dubbed SVD-GCN, which only exploits $K$-largest singular vectors for recommendation. To alleviate the over-smoothing issue, we propose a renormalization trick to adjust the singular value gap, resulting in significant improvement. Extensive experiments on three real-world datasets show that our proposed SVD-GCN not only significantly outperforms state-of-the-arts but also achieves over 100x and 10x speedups over LightGCN and MF, respectively.","url_abs":"https://arxiv.org/abs/2208.12689v2","url_pdf":"https://arxiv.org/pdf/2208.12689v2.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":"svd-gcn-a-simplified-graph-convolution","repo_url":"https://github.com/tanatosuu/svd_gcn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"lightgcn","method_name":"LightGCN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.12689","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}