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

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.

References in corpus (16)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• DeepWalk: Online Learning of Social Representations
• Categorical Reparameterization with Gumbel-Softmax
• Mean-field theory for scale-free random networks
• Modern temporal network theory: A colloquium
• Wasserstein GAN
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Dynamic stochastic blockmodels for time-evolving social networks
• NetGAN: Generating Graphs via Random Walks
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
• A Test of Relative Similarity For Model Selection in Generative Models
• Stochastic Block Transition Models for Dynamic Networks
• Exact ICL maximization in a non-stationary temporal extension of the stochastic block model for dynamic networks
• Efficient Representation Learning Using Random Walks for Dynamic Graphs

Cited by in corpus (4)

• Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problems
• Controllable Data Generation by Deep Learning: A Review
• Deep Generation of Heterogeneous Networks
• Efficient Learning-based Graph Simulation for Temporal Graphs