Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering

• URL: http://arxiv.org/abs/2305.06102v1
• Date: Wed, 10 May 2023 12:42:31 GMT
• Title: Towards Better Graph Representation Learning with Parameterized Decomposition & Filtering
• Authors: Mingqi Yang, Wenjie Feng, Yanming Shen, Bryan Hooi
• Abstract summary: We develop a novel and general framework which unifies many existing GNN models. We show how it helps to enhance the flexibility of GNNs while alleviating the smoothness and amplification issues of existing models.
• Score: 27.374515964364814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Proposing an effective and flexible matrix to represent a graph is a fundamental challenge that has been explored from multiple perspectives, e.g., filtering in Graph Fourier Transforms. In this work, we develop a novel and general framework which unifies many existing GNN models from the view of parameterized decomposition and filtering, and show how it helps to enhance the flexibility of GNNs while alleviating the smoothness and amplification issues of existing models. Essentially, we show that the extensively studied spectral graph convolutions with learnable polynomial filters are constrained variants of this formulation, and releasing these constraints enables our model to express the desired decomposition and filtering simultaneously. Based on this generalized framework, we develop models that are simple in implementation but achieve significant improvements and computational efficiency on a variety of graph learning tasks. Code is available at https://github.com/qslim/PDF.

Related papers

• GrassNet: State Space Model Meets Graph Neural Network [57.62885438406724]
  Graph State Space Network (GrassNet) is a novel graph neural network with theoretical support that provides a simple yet effective scheme for designing arbitrary graph spectral filters. To the best of our knowledge, our work is the first to employ SSMs for the design of graph GNN spectral filters. Extensive experiments on nine public benchmarks reveal that GrassNet achieves superior performance in real-world graph modeling tasks.
  arXiv  Detail & Related papers  (2024-08-16T07:33:58Z)
• SPGNN: Recognizing Salient Subgraph Patterns via Enhanced Graph Convolution and Pooling [25.555741218526464]
  Graph neural networks (GNNs) have revolutionized the field of machine learning on non-Euclidean data such as graphs and networks. We propose a concatenation-based graph convolution mechanism that injectively updates node representations. We also design a novel graph pooling module, called WL-SortPool, to learn important subgraph patterns in a deep-learning manner.
  arXiv  Detail & Related papers  (2024-04-21T13:11:59Z)
• Automated Polynomial Filter Learning for Graph Neural Networks [9.120531252536617]
  Polynomial graph filters have been widely used as guiding principles in the design of Graph Neural Networks (GNNs) Recently, the adaptive learning of the graph filters has demonstrated promising performance for modeling graph signals on both homophilic and heterophilic graphs. We propose Auto-Polynomial, a novel and general automated graph filter learning framework that efficiently learns better filters capable of adapting to various complex graph signals.
  arXiv  Detail & Related papers  (2023-07-16T06:14:12Z)
• Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs [52.52570805621925]
  We investigate efficient learning from higher-order graph convolution and learning directly from adjacency matrix for node classification. We show that the resulting model lead to new graphs and residual scaling parameter. We demonstrate that the proposed methods obtain improved accuracy for node-classification of non-homophilous parameters.
  arXiv  Detail & Related papers  (2022-09-12T04:46:55Z)
• A Piece-wise Polynomial Filtering Approach for Graph Neural Networks [0.45298395481707365]
  Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. These models tend to perform poorly on heterophilic graphs, where connected nodes have different labels. We show that our model achieves performance gains of up to 5% over the state-of-theart models and outperforms existing filter-based approaches in general.
  arXiv  Detail & Related papers  (2021-12-07T05:16:53Z)
• 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)
• Stacked Graph Filter [19.343260981528186]
  We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint. We find that by stacking graph filters with learnable solution parameters, we can build a highly adaptive and robust graph classification model.
  arXiv  Detail & Related papers  (2020-11-22T11:20:14Z)
• 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)
• Data-Driven Learning of Geometric Scattering Networks [74.3283600072357]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2020-10-06T01:20:27Z)
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach [55.44107800525776]
  Graph Convolutional Networks (GCNs) are state-of-the-art graph based representation learning models. In this paper, we revisit GCN based Collaborative Filtering (CF) based Recommender Systems (RS) We show that removing non-linearities would enhance recommendation performance, consistent with the theories in simple graph convolutional networks. We propose a residual network structure that is specifically designed for CF with user-item interaction modeling.
  arXiv  Detail & Related papers  (2020-01-28T04:41:25Z)

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.