On the Power of Heuristics in Temporal Graphs

2025-02-07

AI Summary

This work investigates whether simple heuristics—namely recency and popularity—can match or even surpass state-of-the-art neural network models in temporal graph prediction. Motivated by the limited capacity of existing deep models to capture critical dynamic patterns in real-world temporal graphs, we propose lightweight, interpretable heuristic algorithms and, for the first time, systematically quantify the impact of recency and popularity on predictive performance. We introduce a novel temporal pattern sensitivity metric and conduct comprehensive evaluation on the Temporal Graph Benchmark (achieving SOTA across all datasets) and BenchTemp (achieving top performance on multiple datasets). Results demonstrate that heuristics relying solely on elementary statistical regularities are highly competitive—and more importantly, expose fundamental limitations of current deep models in capturing core temporal dynamics of real-world scenarios. This insight advocates a shift toward finer-grained, mechanism-aware evaluation paradigms. Our code is publicly available.

Technology Category

• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Dynamic graph datasets often exhibit strong temporal patterns, such as recency, which prioritizes recent interactions, and popularity, which favors frequently occurring nodes. We demonstrate that simple heuristics leveraging only these patterns can perform on par or outperform state-of-the-art neural network models under standard evaluation protocols. To further explore these dynamics, we introduce metrics that quantify the impact of recency and popularity across datasets. Our experiments on BenchTemp and the Temporal Graph Benchmark show that our approaches achieve state-of-the-art performance across all datasets in the latter and secure top ranks on multiple datasets in the former. These results emphasize the importance of refined evaluation schemes to enable fair comparisons and promote the development of more robust temporal graph models. Additionally, they reveal that current deep learning methods often struggle to capture the key patterns underlying predictions in real-world temporal graphs. For reproducibility, we have made our code publicly available.

Problem

• Evaluate heuristic performance in temporal graphs.
• Quantify recency and popularity impact metrics.
• Compare heuristics with neural network models.

Innovation

• Leverages temporal patterns effectively
• Introduces recency and popularity metrics
• Achieves state-of-the-art performance benchmarks