Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
- URL: http://arxiv.org/abs/2406.01249v2
- Date: Wed, 30 Oct 2024 13:39:43 GMT
- Title: Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
- Authors: Ya-Wei Eileen Lin, Ronen Talmon, Ron Levie,
- Abstract summary: We consider the graph functional shifts as the symmetry group: the unitary operators that commute with the graph shift operator.
We propose nonlinear spectral filters (NLSFs) that are fully equivariant to graph functional shifts.
We demonstrate the superior performance of NLSFs over existing spectral GNNs in node and graph classification benchmarks.
- Score: 12.709930975472698
- License:
- Abstract: Equivariant machine learning is an approach for designing deep learning models that respect the symmetries of the problem, with the aim of reducing model complexity and improving generalization. In this paper, we focus on an extension of shift equivariance, which is the basis of convolution networks on images, to general graphs. Unlike images, graphs do not have a natural notion of domain translation. Therefore, we consider the graph functional shifts as the symmetry group: the unitary operators that commute with the graph shift operator. Notably, such symmetries operate in the signal space rather than directly in the spatial space. We remark that each linear filter layer of a standard spectral graph neural network (GNN) commutes with graph functional shifts, but the activation function breaks this symmetry. Instead, we propose nonlinear spectral filters (NLSFs) that are fully equivariant to graph functional shifts and show that they have universal approximation properties. The proposed NLSFs are based on a new form of spectral domain that is transferable between graphs. We demonstrate the superior performance of NLSFs over existing spectral GNNs in node and graph classification benchmarks.
Related papers
- Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts [57.19908334882441]
Dynamic graph neural networks (DyGNNs) currently struggle with handling distribution shifts that are inherent in dynamic graphs.
We propose to study distribution shifts on dynamic graphs in the spectral domain for the first time.
arXiv Detail & Related papers (2024-03-08T04:07:23Z) - HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs.
Here we show this traditional reliance on the graph Fourier transform to be superfluous.
We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
arXiv Detail & Related papers (2023-10-03T17:42:09Z) - Approximately Equivariant Graph Networks [14.312312714312046]
Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph.
We focus on the active symmetries of GNNs, by considering a learning setting where signals are supported on a fixed graph.
arXiv Detail & Related papers (2023-08-21T03:13:38Z) - Geometric Graph Filters and Neural Networks: Limit Properties and
Discriminability Trade-offs [122.06927400759021]
We study the relationship between a graph neural network (GNN) and a manifold neural network (MNN) when the graph is constructed from a set of points sampled from the manifold.
We prove non-asymptotic error bounds showing that convolutional filters and neural networks on these graphs converge to convolutional filters and neural networks on the continuous manifold.
arXiv Detail & Related papers (2023-05-29T08:27:17Z) - Stable and Transferable Hyper-Graph Neural Networks [95.07035704188984]
We introduce an architecture for processing signals supported on hypergraphs via graph neural networks (GNNs)
We provide a framework for bounding the stability and transferability error of GNNs across arbitrary graphs via spectral similarity.
arXiv Detail & Related papers (2022-11-11T23:44:20Z) - How Powerful are Spectral Graph Neural Networks [9.594432031144715]
Spectral Graph Neural Network is a kind of Graph Neural Network based on graph signal filters.
We first prove that even spectral GNNs without nonlinearity can produce arbitrary graph signals.
We also establish a connection between the expressive power of spectral GNNs and Graph Isomorphism (GI) testing.
arXiv Detail & Related papers (2022-05-23T10:22:12Z) - Spectral-Spatial Global Graph Reasoning for Hyperspectral Image
Classification [50.899576891296235]
Convolutional neural networks have been widely applied to hyperspectral image classification.
Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
arXiv Detail & Related papers (2021-06-26T06:24:51Z) - Graphon Pooling in Graph Neural Networks [169.09536309161314]
Graph neural networks (GNNs) have been used effectively in different applications involving the processing of signals on irregular structures modeled by graphs.
We propose a new strategy for pooling and sampling on GNNs using graphons which preserves the spectral properties of the graph.
arXiv Detail & Related papers (2020-03-03T21:04:20Z)
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.