HoloNets: Spectral Convolutions do extend to Directed Graphs

• URL: http://arxiv.org/abs/2310.02232v2
• Date: Fri, 10 Nov 2023 15:34:22 GMT
• Title: HoloNets: Spectral Convolutions do extend to Directed Graphs
• Authors: Christian Koke, Daniel Cremers
• Abstract summary: 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.
• Score: 59.851175771106625
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Within the graph learning community, conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs: Only there could the existence of a well-defined graph Fourier transform be guaranteed, so that information may be translated between spatial- and spectral domains. Here we show this traditional reliance on the graph Fourier transform to be superfluous and -- making use of certain advanced tools from complex analysis and spectral theory -- extend spectral convolutions to directed graphs. 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. In order to thoroughly test the developed theory, we conduct experiments in real world settings, showcasing that directed spectral convolutional networks provide new state of the art results for heterophilic node classification on many datasets and -- as opposed to baselines -- may be rendered stable to resolution-scale varying topological perturbations.

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)
• 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)
• Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering [31.595664867365322]
  spectral Graph Neural Networks (GNNs) are well-founded in the spectral domain, but their practical reliance on approximation implies a profound linkage to the spatial domain. We establish a theoretical connection between spectral and spatial aggregation, unveiling an intrinsic interaction that spectral implicitly leads the original graph to an adapted new graph. We propose a novel Spatially Adaptive Filtering (SAF) framework, which leverages the adapted new graph by spectral filtering for an auxiliary non-local aggregation.
  arXiv  Detail & Related papers  (2024-01-17T09:12:31Z)
• 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)
• Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph Wavelets [81.63035727821145]
  Spectral graph convolutional networks (SGCNs) have been attracting increasing attention in graph representation learning. We propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.
  arXiv  Detail & Related papers  (2021-08-03T17:57:53Z)
• 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)
• An Experimental Study of the Transferability of Spectral Graph Networks [5.736353542430439]
  Spectral graph convolutional networks are generalizations of standard convolutional networks for graph-structured data using the Laplacian operator. Recent works have proved the stability of spectral filters under graph benchmarks.
  arXiv  Detail & Related papers  (2020-12-18T14:15:07Z)
• Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks [8.563354084119062]
  We show some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain.
  arXiv  Detail & Related papers  (2020-03-26T01:49:24Z)

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.