Scalable Deep Metric Learning on Attributed Graphs

Abstract

We consider the problem of constructing embeddings of large attributed graphs and supporting multiple downstream learning tasks. We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques to 1) work with attributed graphs, 2) enabling a mini-batch based approach, and 3) achieving scalability. Based on a multi-class tuplet loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case. Analyzing our methods, we provide a generalization bound for the downstream node classification task and for the first time relate tuplet loss to contrastive learning. Through extensive experiments, we show high scalability of representation construction, and in applying the method for three downstream tasks (node clustering, node classification, and link prediction) better consistency over any single existing method.

This is the complete version of a published paper with appendix including detailed proofs

References in corpus (7)

• Modularity and community structure in networks
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• DeepWalk: Online Learning of Social Representations
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Graph Contrastive Learning with Adaptive Augmentation
• Structural Deep Clustering Network
• Adaptive Graph Encoder for Attributed Graph Embedding