Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption

TL;DR

FUEL is an unsupervised node embedding method that adaptively adjusts graph convolution based on node features, improving performance on both homophilic and non-homophilic graphs.

Contribution

It introduces a novel adaptive approach to control graph convolution in unsupervised learning using feature-based clustering as class proxies.

Findings

Achieves state-of-the-art results on diverse benchmark datasets.

Effectively handles non-homophilic graphs.

Outperforms 15 baseline methods in downstream tasks.

Abstract

Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.