Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials
Keywords: Heterogeneous Graph Neural Networks, Spectral Graph Convolutions, Positive Noncommutative Polynomials, Graph Optimization.
TL;DR: This paper introduces PSHGCN, a novel spectral heterogeneous convolutional network using positive noncommutative polynomials, achieving superior performance and scaling to a million graph.
Abstract: Heterogeneous Graph Neural Networks (HGNNs) have gained significant popularity in various heterogeneous graph learning tasks. However, most existing HGNNs rely on spatial domain-based methods to aggregate information, i.e., manually selected meta-paths or some heuristic modules, lacking theoretical guarantees. Furthermore, these methods cannot learn arbitrary valid heterogeneous graph filters within the spectral domain, which have limited expressiveness. To tackle these issues, we present a positive spectral heterogeneous graph convolution via positive noncommutative polynomials. Then, using this convolution, we propose PSHGCN, a novel heterogeneous graph convolutional network. PSHGCN offers a simple yet effective method for learning valid heterogeneous graph filters. Moreover, we demonstrate the rationale of PSHGCN in the graph optimization framework. We conducted an extensive experimental study to show that PSHGCN can learn diverse heterogeneous graph filters and outperform all baselines on open benchmarks. Notably, PSHGCN exhibits remarkable scalability, efficiently handling large real-world graphs comprising millions of nodes and edges. Our codes are available in the anonymous link: https://anonymous.4open.science/r/PSHGCN_Code-DFDC.
Track: Graph Algorithms and Learning for the Web
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 1217
Loading