TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models

TL;DR

TG-GAN introduces a novel continuous-time generative model for temporal graphs, effectively capturing dynamic topology and attributes, and outperforming existing methods in synthetic and real-world datasets.

Contribution

It proposes a new deep generative adversarial network for temporal graphs that models continuous-time evolution and enforces temporal validity constraints.

Findings

TG-GAN outperforms existing methods in efficiency and effectiveness.

The model accurately captures dynamic graph topology and attributes.

Extensive experiments validate the approach on synthetic and real datasets.

Abstract

The recent deep generative models for static graphs that are now being actively developed have achieved significant success in areas such as molecule design. However, many real-world problems involve temporal graphs whose topology and attribute values evolve dynamically over time, including important applications such as protein folding, human mobility networks, and social network growth. As yet, deep generative models for temporal graphs are not yet well understood and existing techniques for static graphs are not adequate for temporal graphs since they cannot 1) encode and decode continuously-varying graph topology chronologically, 2) enforce validity via temporal constraints, or 3) ensure efficiency for information-lossless temporal resolution. To address these challenges, we propose a new model, called ``Temporal Graph Generative Adversarial Network'' (TG-GAN) for continuous-time temporal graph generation, by modeling the deep generative process for truncated temporal random walks and their compositions. Specifically, we first propose a novel temporal graph generator that jointly model truncated edge sequences, time budgets, and node attributes, with novel activation functions that enforce temporal validity constraints under recurrent architecture. In addition, a new temporal graph discriminator is proposed, which combines time and node encoding operations over a recurrent architecture to distinguish the generated sequences from the real ones sampled by a newly-developed truncated temporal random walk sampler. Extensive experiments on both synthetic and real-world datasets demonstrate TG-GAN significantly outperforms the comparison methods in efficiency and effectiveness.