Maximal Coding Rate Reduction for Graph Embeddings
Abstract
Maximal Coding Rate Reduction (MCRR or MCR<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>) has shown its power in image learning. However, few efforts have been made to bring this novel principle to graph learning. In this paper, we investigate the application of the principle of MCR<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> on graph learning. A Graph Neural Network (GNN) model underpinned by the principle of MCR<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> is proposed to learn the inherent structures of graphs and produce the graph representations or graph embeddings. The proposed model is applied to the TUDataset, a publicly available dataset encompassing many benchmark datasets for graph classification tasks. The discriminative power of the proposed model is empirically assessed by the downstream graph classification tasks based on the embeddings learned in an unsupervised setting.
BibTeX
@inproceedings{icassp2024_maximalcodingrat,
title = {Maximal Coding Rate Reduction for Graph Embeddings},
author = {Zhengyang Chi and Junbin Gao},
booktitle = {ICASSP 2024},
year = {2024}
}