CKGConv: General Graph Convolution with Continuous Kernels

• URL: http://arxiv.org/abs/2404.13604v2
• Date: Wed, 5 Jun 2024 12:54:39 GMT
• Title: CKGConv: General Graph Convolution with Continuous Kernels
• Authors: Liheng Ma, Soumyasundar Pal, Yitian Zhang, Jiaming Zhou, Yingxue Zhang, Mark Coates,
• Abstract summary: We propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv) We show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets.
• Score: 24.58050212186722
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a general convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel and general graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits a stronger expressiveness, as powerful as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets. The code and models are publicly available at https://github.com/networkslab/CKGConv.

Related papers

• Scalable Graph Compressed Convolutions [68.85227170390864]
  We propose a differentiable method that applies permutations to calibrate input graphs for Euclidean convolution. Based on the graph calibration, we propose the Compressed Convolution Network (CoCN) for hierarchical graph representation learning.
  arXiv  Detail & Related papers  (2024-07-26T03:14:13Z)
• Graph Edge Representation via Tensor Product Graph Convolutional Representation [23.021660625582854]
  This paper defines an effective convolution operator on graphs with edge features which is named as Product Graph Convolution (TPGC) It provides a complementary model to traditional graph convolutions (GCs) to address the more general graph data analysis with both node and edge features. Experimental results on several graph learning tasks demonstrate the effectiveness of the proposed TPGC.
  arXiv  Detail & Related papers  (2024-06-21T03:21:26Z)
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data [91.27527985415007]
  Existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph. We advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set.
  arXiv  Detail & Related papers  (2023-06-05T07:53:52Z)
• A Graph Convolution for Signed Directed Graphs [0.0]
  Graph convolutions for signed directed graphs have not been delivered much yet. We propose a novel complex Hermitian adjacency matrix that encodes graph information via complex numbers. To the best of our knowledge, it is the first spectral convolution for graphs with signs.
  arXiv  Detail & Related papers  (2022-08-23T01:58:35Z)
• Demystifying Graph Convolution with a Simple Concatenation [6.542119695695405]
  We quantify the information overlap between graph topology, node features, and labels. We show that graph concatenation is a simple but more flexible alternative to graph convolution.
  arXiv  Detail & Related papers  (2022-07-18T16:39:33Z)
• Pure Transformers are Powerful Graph Learners [51.36884247453605]
  We show that standard Transformers without graph-specific modifications can lead to promising results in graph learning both in theory and practice. We prove that this approach is theoretically at least as expressive as an invariant graph network (2-IGN) composed of equivariant linear layers. Our method coined Tokenized Graph Transformer (TokenGT) achieves significantly better results compared to GNN baselines and competitive results.
  arXiv  Detail & Related papers  (2022-07-06T08:13:06Z)
• Graph Kernel Neural Networks [53.91024360329517]
  We propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability.
  arXiv  Detail & Related papers  (2021-12-14T14:48:08Z)
• A Generalization of Transformer Networks to Graphs [5.736353542430439]
  We introduce a graph transformer with four new properties compared to the standard model. The architecture is extended to edge feature representation, which can be critical to tasks s.a. chemistry (bond type) or link prediction (entity relationship in knowledge graphs)
  arXiv  Detail & Related papers  (2020-12-17T16:11:47Z)
• Factorizable Graph Convolutional Networks [90.59836684458905]
  We introduce a novel graph convolutional network (GCN) that explicitly disentangles intertwined relations encoded in a graph. FactorGCN takes a simple graph as input, and disentangles it into several factorized graphs. We evaluate the proposed FactorGCN both qualitatively and quantitatively on the synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-10-12T03:01:40Z)
• Dirichlet Graph Variational Autoencoder [65.94744123832338]
  We present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships.
  arXiv  Detail & Related papers  (2020-10-09T07:35:26Z)

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.