Efficient Graph Condensation via Gaussian Process

TL;DR

This paper introduces GCGP, a novel graph condensation method using Gaussian Processes that efficiently reduces large graph sizes while maintaining predictive accuracy, overcoming the scalability issues of traditional GNN training.

Contribution

GCGP is a new, computationally efficient graph condensation approach that leverages Gaussian Processes and specialized covariance functions to capture dependencies and optimize binary graph structures.

Findings

GCGP effectively condenses large graphs with minimal performance loss.

The method significantly reduces computational resources compared to existing techniques.

Experimental results demonstrate GCGP's scalability and accuracy in large-scale graph datasets.

Abstract

Graph condensation reduces the size of large graphs while preserving performance, addressing the scalability challenges of Graph Neural Networks caused by computational inefficiencies on large datasets. Existing methods often rely on bi-level optimization, requiring extensive GNN training and limiting their scalability. To address these issues, this paper proposes Graph Condensation via Gaussian Process (GCGP), a novel and computationally efficient approach to graph condensation. GCGP utilizes a Gaussian Process (GP), with the condensed graph serving as observations, to estimate the posterior distribution of predictions. This approach eliminates the need for the iterative and resource-intensive training typically required by GNNs. To enhance the capability of the GCGP in capturing dependencies between function values, we derive a specialized covariance function that incorporates structural information. This covariance function broadens the receptive field of input nodes by local neighborhood aggregation, thereby facilitating the representation of intricate dependencies within the nodes. To address the challenge of optimizing binary structural information in condensed graphs, Concrete random variables are utilized to approximate the binary adjacency matrix in a continuous counterpart. This relaxation process allows the adjacency matrix to be represented in a differentiable form, enabling the application of gradient-based optimization techniques to discrete graph structures. Experimental results show that the proposed GCGP method efficiently condenses large-scale graph data while preserving predictive performance, addressing the scalability and efficiency challenges. The implementation of our method is publicly available at https://github.com/WANGLin0126/GCGP.