{"ID":2837896,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.18279","arxiv_id":"2511.18279","title":"Democratic Recommendation with User and Item Representatives Produced by Graph Condensation","abstract":"The challenges associated with large-scale user-item interaction graphs have attracted increasing attention in graph-based recommendation systems, primarily due to computational inefficiencies and inadequate information propagation. Existing methods provide partial solutions but suffer from notable limitations: model-centric approaches, such as sampling and aggregation, often struggle with generalization, while data-centric techniques, including graph sparsification and coarsening, lead to information loss and ineffective handling of bipartite graph structures. Recent advances in graph condensation offer a promising direction by reducing graph size while preserving essential information, presenting a novel approach to mitigating these challenges. Inspired by the principles of democracy, we propose \\textbf{DemoRec}, a framework that leverages graph condensation to generate user and item representatives for recommendation tasks. By constructing a compact interaction graph and clustering nodes with shared characteristics from the original graph, DemoRec significantly reduces graph size and computational complexity. Furthermore, it mitigates the over-reliance on high-order information, a critical challenge in large-scale bipartite graphs. Extensive experiments conducted on four public datasets demonstrate the effectiveness of DemoRec, showcasing substantial improvements in recommendation performance, computational efficiency, and robustness compared to SOTA methods.","short_abstract":"The challenges associated with large-scale user-item interaction graphs have attracted increasing attention in graph-based recommendation systems, primarily due to computational inefficiencies and inadequate information propagation. Existing methods provide partial solutions but suffer from notable limitations: model-c...","url_abs":"https://arxiv.org/abs/2511.18279","url_pdf":"https://arxiv.org/pdf/2511.18279v1","authors":"[\"Jiahao Liang\",\"Haoran Yang\",\"Xiangyu Zhao\",\"Zhiwen Yu\",\"Guandong Xu\",\"Wanyu Wang\",\"Kaixiang Yang\"]","published":"2025-11-23T04:09:28Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false}