@inproceedings{shen2021how,
author = {Shen, Yifei and Wu, Yongji and Zhang, Yao and Shan, Caihua and Zhang, Jun and Letaief, Khaled Ben and Li, Dongsheng},
title = {How Powerful is Graph Convolution for Recommendation?},
booktitle = {Conference on Information and Knowledge Management (Oral)},
year = {2021},
month = {November},
abstract = {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.},
url = {http://approjects.co.za/?big=en-us/research/publication/how-powerful-is-graph-convolution-for-recommendation/},
note = {Project: Inductive bias in neural architectures},
}