T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs

• URL: http://arxiv.org/abs/2507.10183v2
• Date: Tue, 22 Jul 2025 16:14:41 GMT
• Title: T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
• Authors: Alireza Dizaji, Benedict Aaron Tjandra, Mehrab Hamidi, Shenyang Huang, Guillaume Rabusseau,
• Abstract summary: We introduce the Temporal Graph Reasoning Benchmark (T-GRAB) to systematically probe the capabilities of TGNNs to reason across time.<n>T-GRAB provides controlled, interpretable tasks that isolate key temporal skills.<n>We evaluate 11 temporal graph learning methods on these tasks, revealing fundamental shortcomings in their ability to generalize temporal patterns.
• Score: 6.199165061105655
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dynamic graph learning methods have recently emerged as powerful tools for modelling relational data evolving through time. However, despite extensive benchmarking efforts, it remains unclear whether current Temporal Graph Neural Networks (TGNNs) effectively capture core temporal patterns such as periodicity, cause-and-effect, and long-range dependencies. In this work, we introduce the Temporal Graph Reasoning Benchmark (T-GRAB), a comprehensive set of synthetic tasks designed to systematically probe the capabilities of TGNNs to reason across time. T-GRAB provides controlled, interpretable tasks that isolate key temporal skills: counting/memorizing periodic repetitions, inferring delayed causal effects, and capturing long-range dependencies over both spatial and temporal dimensions. We evaluate 11 temporal graph learning methods on these tasks, revealing fundamental shortcomings in their ability to generalize temporal patterns. Our findings offer actionable insights into the limitations of current models, highlight challenges hidden by traditional real-world benchmarks, and motivate the development of architectures with stronger temporal reasoning abilities. The code for T-GRAB can be found at: https://github.com/alirezadizaji/T-GRAB.

Related papers

• Mind the truncation gap: challenges of learning on dynamic graphs with recurrent architectures [10.434476078553786]
  Continuous-time dynamic graphs (CTDGs) pose challenges for machine learning (ML) approaches.<n>We show that a short truncation of backpropagation-through-time (BPTT) can limit the learning of dependencies beyond a single hop.<n>We argue that understanding and addressing this gap is essential as the importance of CTDGs grows.
  arXiv  Detail & Related papers  (2024-12-30T16:07:41Z)
• ST-FiT: Inductive Spatial-Temporal Forecasting with Limited Training Data [59.78770412981611]
  In real-world applications, most nodes may not possess any available temporal data during training.<n>We propose a principled framework named ST-FiT to handle this problem.
  arXiv  Detail & Related papers  (2024-12-14T17:51:29Z)
• Deep-Graph-Sprints: Accelerated Representation Learning in Continuous-Time Dynamic Graphs [4.372841335228306]
  Continuous-time dynamic graphs (CTDGs) are essential for modeling interconnected, evolving systems. Deep-Graph-Sprints (DGS) is a novel deep learning architecture designed for efficient representation learning on CTDGs with low-latency inference requirements.
  arXiv  Detail & Related papers  (2024-07-10T14:44:25Z)
• Long Range Propagation on Continuous-Time Dynamic Graphs [18.5534584418248]
  Continuous-Time Graph Anti-Symmetric Network (CTAN) is designed for efficient propagation of information. We show how CTAN's empirical performance on synthetic long-range benchmarks and real-world benchmarks is superior to other methods.
  arXiv  Detail & Related papers  (2024-06-04T19:42:19Z)
• LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning [61.4707298969173]
  We introduce LasTGL, an industrial framework that integrates unified and unified implementations of common temporal graph learning algorithms. LasTGL provides comprehensive temporal graph datasets, TGNN models and utilities along with well-documented tutorials.
  arXiv  Detail & Related papers  (2023-11-28T08:45:37Z)
• Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs [10.034072706245544]
  We propose a Time-aware Graph Structure Learning (TGSL) approach via sequence prediction on temporal graphs. In particular, it predicts time-aware context embedding and uses the Gumble-Top-K to select the closest candidate edges to this context embedding. Experiments on temporal link prediction benchmarks demonstrate that TGSL yields significant gains for the popular TGNs such as TGAT and GraphMixer.
  arXiv  Detail & Related papers  (2023-06-13T11:34:36Z)
• Deep Temporal Graph Clustering [77.02070768950145]
  We propose a general framework for deep Temporal Graph Clustering (GC) GC introduces deep clustering techniques to suit the interaction sequence-based batch-processing pattern of temporal graphs. Our framework can effectively improve the performance of existing temporal graph learning methods.
  arXiv  Detail & Related papers  (2023-05-18T06:17:50Z)
• TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification [6.76723360505692]
  We propose a novel temporal dynamic neural graph network (TodyNet) that can extract hidden-temporal dependencies without undefined graph structure. The experiments on 26 UEA benchmark datasets illustrate that the proposed TodyNet outperforms existing deep learning-based methods in the MTSC tasks.
  arXiv  Detail & Related papers  (2023-04-11T09:21:28Z)
• EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning [92.71579608528907]
  This paper aims to design an easy-to-use pipeline (termed as EasyDGL) composed of three key modules with both strong ability fitting and interpretability. EasyDGL can effectively quantify the predictive power of frequency content that a model learn from the evolving graph data.
  arXiv  Detail & Related papers  (2023-03-22T06:35:08Z)
• Space-Time Graph Neural Networks with Stochastic Graph Perturbations [100.31591011966603]
  Space-time graph neural networks (ST-GNNs) learn efficient graph representations of time-varying data. In this paper we revisit the properties of ST-GNNs and prove that they are stable to graph stabilitys. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs.
  arXiv  Detail & Related papers  (2022-10-28T16:59:51Z)
• Temporal Knowledge Graph Reasoning with Low-rank and Model-agnostic Representations [1.8262547855491458]
  We introduce Time-LowFER, a family of parameter-efficient and time-aware extensions of the low-rank tensor factorization model LowFER. Noting several limitations in current approaches to represent time, we propose a cycle-aware time-encoding scheme for time features. We implement our methods in a unified temporal knowledge graph embedding framework, focusing on time-sensitive data processing.
  arXiv  Detail & Related papers  (2022-04-10T22:24:11Z)
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs [65.18780403244178]
  We propose a continuous model to forecast Multivariate Time series with dynamic Graph neural Ordinary Differential Equations (MTGODE) Specifically, we first abstract multivariate time series into dynamic graphs with time-evolving node features and unknown graph structures. Then, we design and solve a neural ODE to complement missing graph topologies and unify both spatial and temporal message passing.
  arXiv  Detail & Related papers  (2022-02-17T02:17:31Z)

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.