Stacked Graph Filter
- URL: http://arxiv.org/abs/2011.10988v1
- Date: Sun, 22 Nov 2020 11:20:14 GMT
- Title: Stacked Graph Filter
- Authors: Hoang NT and Takanori Maehara and Tsuyoshi Murata
- Abstract summary: 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.
- Score: 19.343260981528186
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study Graph Convolutional Networks (GCN) from the graph signal processing
viewpoint by addressing a difference between learning graph filters with fully
connected weights versus trainable polynomial coefficients. We find that by
stacking graph filters with learnable polynomial parameters, we can build a
highly adaptive and robust vertex classification model. Our treatment here
relaxes the low-frequency (or equivalently, high homophily) assumptions in
existing vertex classification models, resulting a more ubiquitous solution in
terms of spectral properties. Empirically, by using only one hyper-parameter
setting, our model achieves strong results on most benchmark datasets across
the frequency spectrum.
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) - Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach [36.06398179717066]
We develop an adaptive graph filter based on Krylov subspaces to filter complex graphs.
We conduct extensive experiments across a series of real-world datasets.
arXiv Detail & Related papers (2024-03-12T06:26:17Z) - An Effective Universal Polynomial Basis for Spectral Graph Neural
Networks [12.725906836609811]
Spectral Graph Neural Networks (GNNs) have gained increasing prevalence for heterophily graphs.
We develop an adaptive heterophily basis by incorporating graph heterophily degrees.
We then integrate this heterophily basis with the homophily basis, creating a universal basis UniBasis.
arXiv Detail & Related papers (2023-11-30T01:48:42Z) - Specformer: Spectral Graph Neural Networks Meet Transformers [51.644312964537356]
Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions.
We introduce Specformer, which effectively encodes the set of all eigenvalues and performs self-attention in the spectral domain.
By stacking multiple Specformer layers, one can build a powerful spectral GNN.
arXiv Detail & Related papers (2023-03-02T07:36:23Z) - 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) - Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets [3.2498534294827044]
We propose a process model using spectral graph wavelets, which can aggregate information at different scales.
We achieve scalability to larger graphs by using a spectrum-adaptive approximation of the filter function, which is designed to yield a low approximation error in dense areas of the graph spectrum.
arXiv Detail & Related papers (2021-10-25T09:25:04Z) - Message Passing in Graph Convolution Networks via Adaptive Filter Banks [81.12823274576274]
We present a novel graph convolution operator, termed BankGCN.
It decomposes multi-channel signals on graphs into subspaces and handles particular information in each subspace with an adapted filter.
It achieves excellent performance in graph classification on a collection of benchmark graph datasets.
arXiv Detail & Related papers (2021-06-18T04:23:34Z) - 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) - 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) - Gaussian Processes on Graphs via Spectral Kernel Learning [9.260186030255081]
We propose a graph spectrum-based Gaussian process for prediction of signals defined on nodes of the graph.
We demonstrate the interpretability of the model in synthetic experiments from which we show the various ground truth spectral filters can be accurately recovered.
arXiv Detail & Related papers (2020-06-12T17:51:22Z)
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.