TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs

2026-09-08

AI Summary

为解决现有基准在语义演化支持上的不足，TTGBench通过六个真实文本丰富的数据集，评估结构和语义演变，填补了多类与多标签TNC的空白。

Abstract

Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time. However, existing benchmarks primarily emphasize structural evolution via temporal link prediction (TLP), while support for semantic evolution remains limited. Although temporal node classification (TNC) is sometimes included, it is typically restricted to simplistic binary settings that fail to capture realistic semantic drift. Moreover, commonly used datasets exhibit high link repetition, leading to inflated performance estimates and obscuring true model capability. To address these limitations, we introduce \textbf{TTGBench}, a new benchmark that jointly evaluates structural and semantic evolution. TTGBench comprises six real-world, text-rich datasets characterized by \emph{Dual Volatility}, enabling rigorous and fair evaluation of existing models. Notably, it is the first benchmark to support both multi-class and multi-label TNC, filling a critical gap in evaluating temporal semantic drift. We conduct a comprehensive evaluation of 17 state-of-the-art methods across Temporal Graph Neural Networks (TGNNs) and Large Language Model (LLM)-based paradigms. The results reveal a clear \emph{capability divide} between the two paradigms: TGNN-based methods excel at structural prediction but fail at semantic tracking, whereas LLM-based predictors show the opposite trend. Through in-depth analysis, we uncover their fundamental limitations and provide insights for developing more comprehensive temporal graph models.

Problem

• Temporal Graph Learning
• Semantic Drift
• Structural Evolution

Innovation

• Dual Volatility
• Temporal Node Classification (TNC)
• Semantic Drift
• Temporal Graph Neural Networks (TGNNs)
• Large Language Models (LLMs)