Representation Learning over Dynamic Graphs

TL;DR

This paper introduces DyRep, a deep learning framework for encoding evolving information in dynamic graphs into low-dimensional embeddings, capturing complex nonlinear temporal dynamics for improved link and event prediction.

Contribution

The paper presents DyRep, a novel inductive learning method that models complex temporal dynamics in evolving graphs using a multivariate point process, outperforming existing baselines.

Findings

Significantly outperforms baselines on dynamic link prediction

Effectively models complex nonlinear temporal dynamics

Demonstrates strong results on real-world datasets

Abstract

How can we effectively encode evolving information over dynamic graphs into low-dimensional representations? In this paper, we propose DyRep, an inductive deep representation learning framework that learns a set of functions to efficiently produce low-dimensional node embeddings that evolves over time. The learned embeddings drive the dynamics of two key processes namely, communication and association between nodes in dynamic graphs. These processes exhibit complex nonlinear dynamics that evolve at different time scales and subsequently contribute to the update of node embeddings. We employ a time-scale dependent multivariate point process model to capture these dynamics. We devise an efficient unsupervised learning procedure and demonstrate that our approach significantly outperforms representative baselines on two real-world datasets for the problem of dynamic link prediction and event time prediction.