Graph-Structured Gaussian Processes for Transferable Graph Learning
Jun Wu, Lisa Ainsworth, Andrew Leakey, Haixun Wang, Jingrui He
Abstract
Transferable graph learning involves knowledge transferability from a source graph to a relevant target graph. The major challenge of transferable graph learning is the distribution shift between source and target graphs induced by individual node attributes and complex graph structures. To solve this problem, in this paper, we propose a generic graph-structured Gaussian process framework (GraphGP) for adaptively transferring knowledge across graphs with either homophily or heterophily assumptions. Specifically, GraphGP is derived from a novel graph structure-aware neural network in the limit on the layer width. The generalization analysis of GraphGP explicitly investigates the connection between knowledge transferability and graph domain similarity. Extensive experiments on several transferable graph learning benchmarks demonstrate the efficacy of GraphGP over state-of-the-art Gaussian process baselines.
BibTeX
@inproceedings{
wu2023graphstructured,
title={Graph-Structured Gaussian Processes for Transferable Graph Learning},
author={Jun Wu and Lisa Ainsworth and Andrew Leakey and Haixun Wang and Jingrui He},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=eZbqD9BoXe}
}