Democratic Recommendation with User and Item Representatives Produced by Graph Condensation

TL;DR

DemoRec introduces a graph condensation-based framework that creates user and item representatives, significantly reducing graph size and computational costs while improving recommendation accuracy and robustness.

Contribution

It presents a novel democratic graph condensation approach to generate representative nodes, addressing efficiency and information loss issues in large-scale bipartite graphs.

Findings

Substantial improvement in recommendation accuracy over SOTA methods

Enhanced computational efficiency and scalability

Increased robustness to data sparsity and noise

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.