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

• URL: http://arxiv.org/abs/2609.08226v1
• Date: Tue, 08 Sep 2026 04:19:11 GMT
• Title: TTGBench: Benchmarking Topological Evolution and Semantic Drift in Text-attributed Temporal Graphs
• Abstract summary: Temporal graph learning models the evolution of dynamic systems, where both structural interactions and semantic states change over time.<n>We introduce textbfTTGBench, a new benchmark that jointly evaluates structural and semantic evolution.<n>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.
• Score: 24.36945438269572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series [14.456983509027195]
  We propose Graph Layer for Inference in Dynamic En- vironments (GLIDE), a novel GNN layer enhanced by two theoretically grounded design mechanisms.<n>Experiments on synthetic and real-world benchmarks show that GLIDE improves average performance by up to 45.6% across static and dynamic settings.
  arXiv  Detail & Related papers  (2026-08-07T15:28:45Z)
• Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models [59.8742208800447]
  We propose DyGFM, a Dynamic Graph Foundation Model over multiple domains based on decoupled and divergence-conditioned prompting.<n>We show that DyGFM consistently outperforms 12 state-of-the-art baselines on both node classification and link prediction tasks.
  arXiv  Detail & Related papers  (2026-05-13T13:50:03Z)
• Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework [0.6435984242701042]
  We propose TL-GPSGNT to improve graph-based time series forecasting models.<n>We use information-theoretic and correlation-based criteria to extract structurally informative subgraphs.<n>We show that TL-GPSGNT consistently outperforms baselines in low-data transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-04T02:41:29Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction [16.798673711008906]
  Dynamic graph-level embedding aims to capture structural evolution in networks.<n>Existing methods face two critical yet under-explored issues: Structural Visit Bias and Abrupt Evolution Blindness.<n>We propose EvoFormer, an evolution-aware Transformer framework tailored for dynamic graph-level representation learning.
  arXiv  Detail & Related papers  (2025-08-21T09:19:54Z)
• Towards Foundation Model on Temporal Knowledge Graph Reasoning [17.165969719351125]
  Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t)<n>New model employs sinusoidal positional encodings to capture fine-grained temporal patterns.<n>PostRA demonstrates strong zero-shot performance on unseen temporal knowledge graphs.
  arXiv  Detail & Related papers  (2025-06-04T09:19:49Z)
• Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models [25.780463407652295]
  Temporal graph neural networks (TGNNs) have shown remarkable performance in temporal graph modeling.<n>We present textbfCROSS, a flexible framework that seamlessly extends existing TGNNs for TTAG modeling.
  arXiv  Detail & Related papers  (2025-03-18T16:50:10Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale [54.15522908057831]
  We propose an adapted version of the computationally-Mixer for STTD forecast at scale. Our results surprisingly show that this simple-yeteffective solution can rival SOTA baselines when tested on several traffic benchmarks. Our findings contribute to the exploration of simple-yet-effective models for real-world STTD forecasting.
  arXiv  Detail & Related papers  (2023-07-04T05:19:19Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting [52.47493322446537]
  We develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets.
  arXiv  Detail & Related papers  (2023-05-22T13:39:44Z)
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment [53.72873672076391]
  Temporal graph learning aims to generate high-quality representations for graph-based tasks with dynamic information. We propose a self-supervised method called S2T for temporal graph learning, which extracts both temporal and structural information. S2T achieves at most 10.13% performance improvement compared with the state-of-the-art competitors on several datasets.
  arXiv  Detail & Related papers  (2023-02-15T06:36:04Z)
• SpatioTemporal Focus for Skeleton-based Action Recognition [66.8571926307011]
  Graph convolutional networks (GCNs) are widely adopted in skeleton-based action recognition. We argue that the performance of recent proposed skeleton-based action recognition methods is limited by the following factors. Inspired by the recent attention mechanism, we propose a multi-grain contextual focus module, termed MCF, to capture the action associated relation information.
  arXiv  Detail & Related papers  (2022-03-31T02:45:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.