How Powerful is Graph Filtering for Recommendation

• URL: http://arxiv.org/abs/2406.08827v1
• Date: Thu, 13 Jun 2024 05:37:54 GMT
• Title: How Powerful is Graph Filtering for Recommendation
• Authors: Shaowen Peng, Xin Liu, Kazunari Sugiyama, Tsunenori Mine,
• Abstract summary: We show two limitations suppressing the power of graph filtering. Due to varied noise distribution, graph filters fail to denoise sparse data where noise is scattered across all frequencies. supervised training results in worse performance on dense data where noise is concentrated in middle frequencies that can be removed by graph filters without training.
• Score: 7.523823738965443
• License:
• Abstract: It has been shown that the effectiveness of graph convolutional network (GCN) for recommendation is attributed to the spectral graph filtering. Most GCN-based methods consist of a graph filter or followed by a low-rank mapping optimized based on supervised training. However, we show two limitations suppressing the power of graph filtering: (1) Lack of generality. Due to the varied noise distribution, graph filters fail to denoise sparse data where noise is scattered across all frequencies, while supervised training results in worse performance on dense data where noise is concentrated in middle frequencies that can be removed by graph filters without training. (2) Lack of expressive power. We theoretically show that linear GCN (LGCN) that is effective on collaborative filtering (CF) cannot generate arbitrary embeddings, implying the possibility that optimal data representation might be unreachable. To tackle the first limitation, we show close relation between noise distribution and the sharpness of spectrum where a sharper spectral distribution is more desirable causing data noise to be separable from important features without training. Based on this observation, we propose a generalized graph normalization G^2N to adjust the sharpness of spectral distribution in order to redistribute data noise to assure that it can be removed by graph filtering without training. As for the second limitation, we propose an individualized graph filter (IGF) adapting to the different confidence levels of the user preference that interactions can reflect, which is proved to be able to generate arbitrary embeddings. By simplifying LGCN, we further propose a simplified graph filtering (SGFCF) which only requires the top-K singular values for recommendation. Finally, experimental results on four datasets with different density settings demonstrate the effectiveness and efficiency of our proposed methods.

Related papers

• Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs [60.82508765185161]
  We propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN) DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features. It dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs.
  arXiv  Detail & Related papers  (2024-11-18T04:57:05Z)
• Graph Neural Network Surrogates of Fair Graph Filtering [13.854091527965297]
  We introduce a filter-aware universal approximation framework for posterior objectives. This defines appropriate graph neural networks trained at runtime to be similar to filters. We show that our approach performs equally well or better than alternatives in meeting parity constraints.
  arXiv  Detail & Related papers  (2023-03-14T18:14:40Z)
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering [61.315598419655224]
  We propose Automatic Graph Convolutional Networks (AutoGCN) to capture the full spectrum of graph signals. While it is based on graph spectral theory, our AutoGCN is also localized in space and has a spatial form.
  arXiv  Detail & Related papers  (2021-07-10T04:11:25Z)
• Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
  We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter. We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-26T19:31:21Z)
• FiGLearn: Filter and Graph Learning using Optimal Transport [49.428169585114496]
  We introduce a novel graph signal processing framework for learning the graph and its generating filter from signal observations. We show how this framework can be used to infer missing values if only very little information is available.
  arXiv  Detail & Related papers  (2020-10-29T10:00:42Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Adaptive Graph Encoder for Attributed Graph Embedding [36.06427854846497]
  Attributed graph embedding learns vector representations from graph topology and node features. We propose Adaptive Graph (AGE), a novel attributed graph embedding framework. We conduct experiments using four public benchmark datasets to validate AGE on node clustering and link prediction tasks.
  arXiv  Detail & Related papers  (2020-07-03T10:20:34Z)
• Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation [86.91324735966766]
  Filter is the key component in modern convolutional neural networks (CNNs) In this paper, we introduce filter grafting (textbfMethod) to achieve this goal. We develop a novel criterion to measure the information of filters and an adaptive weighting strategy to balance the grafted information among networks.
  arXiv  Detail & Related papers  (2020-04-26T08:36:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.