How Powerful is Graph Convolution for Recommendation?

2021-08-17 · Yifei Shen, Yongji Wu, Yao Zhang, Caihua Shan, Jun Zhang, Khaled B. Letaief, Dongsheng Li

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.

📄 PDF Abstract BibTeX arXiv:2108.07567

Code (1)

yshenaw/GF_CF 공식 구현 pytorch

Tasks

Collaborative Filtering

Methods 이 논문이 사용한 방법론

LightGCN LightGCN is a type of graph convolutional neural network (GCN), including only the most essential component in GCN (neighborhood…

COHESION: Composite Graph Convolutional Network with Dual-Stage Fusion for Multimodal Recommendation

2025-04-06 · Jinfeng Xu, Zheyu Chen, Wei Wang, Xiping Hu 외

Recent works in multimodal recommendations, which leverage diverse modal information to address data sparsity and enhance recommendation accuracy, have garnered considerable interest. Two key processes in multimodal reco…

Multimodal Recommendation Representation Learning

Graph Cross-Correlated Network for Recommendation

2024-11-02 · Hao Chen, Yuanchen Bei, Wenbing Huang, Shengyuan Chen 외

Collaborative filtering (CF) models have demonstrated remarkable performance in recommender systems, which represent users and items as embedding vectors. Recently, due to the powerful modeling capability of graph neural…

Click-Through Rate Prediction Collaborative Filtering Recommendation Systems

Stability of Graph Neural Networks to Relative Perturbations

2019-10-21 · Fernando Gama, Joan Bruna, Alejandro Ribeiro

Graph neural networks (GNNs), consisting of a cascade of layers applying a graph convolution followed by a pointwise nonlinearity, have become a powerful architecture to process signals supported on graphs. Graph convolu…

Movie Recommendation Recommendation Systems

Simple and Powerful Architecture for Inductive Recommendation Using Knowledge Graph Convolutions

2022-09-09 · Theis E. Jendal, Matteo Lissandrini, Peter Dolog, Katja Hose

Using graph models with relational information in recommender systems has shown promising results. Yet, most methods are transductive, i.e., they are based on dimensionality reduction architectures. Hence, they require h…

Dimensionality Reduction Graph Neural Network Knowledge Graphs Recommendation Systems

Lossless and Privacy-Preserving Graph Convolution Network for Federated Item Recommendation

2024-12-02 · Guowei Wu, Weike Pan, Qiang Yang, Zhong Ming

Graph neural network (GNN) has emerged as a state-of-the-art solution for item recommendation. However, existing GNN-based recommendation methods rely on a centralized storage of fragmented user-item interaction sub-grap…

Graph Neural Network Privacy Preserving