Litcius/Paper detail

Graph Collaborative Signals Denoising and Augmentation for Recommendation

Ziwei Fan, Ke Xu, Dong Zhang, Hao Peng, Jiawei Zhang, Philip S. Yu

202364 citationsDOI

Abstract

Graph collaborative filtering (GCF) is a popular technique for capturing high-order collaborative signals in recommendation systems. However, GCF's bipartite adjacency matrix, which defines the neighbors being aggregated based on user-item interactions, can be noisy for users/items with abundant interactions and insufficient for users/items with scarce interactions. Additionally, the adjacency matrix ignores user-user and item-item correlations, which can limit the scope of beneficial neighbors being aggregated.

Topics & Concepts

Collaborative filteringAdjacency matrixBipartite graphComputer scienceRecommender systemGraphScope (computer science)Adjacency listLimit (mathematics)Information retrievalTheoretical computer scienceAlgorithmMathematicsProgramming languageMathematical analysisRecommender Systems and TechniquesAdvanced Graph Neural NetworksExpert finding and Q&A systems
Graph Collaborative Signals Denoising and Augmentation for Recommendation | Litcius