Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

TL;DR

Contrastive FUSE is a scalable, featureless node embedding method that efficiently combines community structure with pairwise supervision, outperforming existing methods in speed and accuracy.

Contribution

It introduces a spectral contrastive framework that integrates community-aware signals with a lightweight approximation for large-scale, featureless graph node embedding.

Findings

Achieves competitive or superior classification performance without node features.

Offers substantial runtime improvements over existing methods.

Effectively scales to graphs with millions of edges.

Abstract

We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node labels and no available node features. Unlike existing methods, we directly optimize a spectral contrastive objective that integrates community-aware structural signals with signed pairwise constraints. To support large-scale training, we replace the expensive modularity gradient with a lightweight approximation, which preserves the structure-seeking behavior of modularity while reducing the computational cost significantly. This yields an efficient optimization scheme with a natural gradient decomposition and adaptive learning-rate scaling, enabling fast iterative updates even on million-edge graphs. Extensive experiments on benchmark citation networks, large co-purchase graphs, and OGB datasets show that Contrastive FUSE achieves competitive or superior contrastive classification performance without relying on node features, while offering substantial runtime gains over existing baselines. These results highlight the effectiveness of coupling modularity-inspired structural learning with contrastive supervision for efficient and scalable contrastive node representation learning.