Efficient Learning-based Graph Simulation for Temporal Graphs

2025-10-07

AI Summary

Existing temporal graph generation methods suffer from inefficient training, slow inference, and difficulty in jointly preserving both structural and temporal characteristics. To address these challenges, we propose the Temporal Graph Autoencoder (TGAE), an efficient generative framework that integrates a global graph encoder with attention-based spatial-temporal dependency modeling and a local ego-graph–sampling decoder for lightweight, scalable edge generation. During encoding, TGAE captures holistic spatiotemporal patterns; during decoding, it enables fast, localized reconstruction. Compared to state-of-the-art learning-based generators, TGAE achieves superior fidelity in modeling structural evolution and temporal dynamics while significantly improving training speed and inference efficiency. Extensive experiments on multiple real-world and synthetic temporal graph datasets demonstrate that TGAE attains state-of-the-art performance in both generation quality—measured by AUC and MSE—and computational efficiency—measured by training and generation time.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on static graphs, the temporal information of the graphs is ignored. In this paper, we focus on simulating temporal graphs, which aim to reproduce the structural and temporal properties of the observed real-life temporal graphs. In this paper, we first give an overview of the existing temporal graph generators, including recently emerged learning-based approaches. Most of these learning-based methods suffer from one of the limitations: low efficiency in training or slow generating, especially for temporal random walk-based methods. Therefore, we propose an efficient learning-based approach to generate graph snapshots, namely temporal graph autoencoder (TGAE). Specifically, we propose an attention-based graph encoder to encode temporal and structural characteristics on sampled ego-graphs. And we proposed an ego-graph decoder that can achieve a good trade-off between simulation quality and efficiency in temporal graph generation. Finally, the experimental evaluation is conducted among our proposed TGAE and representative temporal graph generators on real-life temporal graphs and synthesized graphs. It is reported that our proposed approach outperforms the state-of-the-art temporal graph generators by means of simulation quality and efficiency.

Problem

• Simulating temporal graphs with structural and temporal properties
• Addressing low efficiency in training and slow generation
• Improving simulation quality and efficiency of graph generators

Innovation

• Learning-based temporal graph autoencoder for simulation
• Attention-based encoder captures temporal structural features
• Ego-graph decoder balances quality and generation efficiency