TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs

• URL: http://arxiv.org/abs/2510.07586v1
• Date: Wed, 08 Oct 2025 22:20:05 GMT
• Title: TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
• Abstract summary: We introduce Temporal Graph Modelling (TGM), a research-oriented library for Machine Learning on temporal graphs.<n>TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks.<n> Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib.
• Score: 45.81179802109882
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored to specific architectures, hindering support for diverse models in this rapidly evolving field. Additionally, the divide between continuous- and discrete-time dynamic graph methods (CTDG and DTDG) limits direct comparisons and idea transfer. To address these gaps, we introduce Temporal Graph Modelling (TGM), a research-oriented library for ML on temporal graphs, the first to unify CTDG and DTDG approaches. TGM offers first-class support for dynamic node features, time-granularity conversions, and native handling of link-, node-, and graph-level tasks. Empirically, TGM achieves an average 7.8x speedup across multiple models, datasets, and tasks compared to the widely used DyGLib, and an average 175x speedup on graph discretization relative to available implementations. Beyond efficiency, we show in our experiments how TGM unlocks entirely new research possibilities by enabling dynamic graph property prediction and time-driven training paradigms, opening the door to questions previously impractical to study. TGM is available at https://github.com/tgm-team/tgm

Related papers

• 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)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• Adaptive Tokenization: On the Hop-Overpriority Problem in Tokenized Graph Learning Models [59.98982735197465]
  Tokenized Graph Learning Models (TGLMs) convert graphs into ordered token lists for scalable processing.<n>TGLMs rely on hand-designed token lists and their adaptability to diverse graph learning scenarios remains unexplored.<n>We propose Learnable Graph Token List (LGTL), a plug-and-play module to replace hand-designed token lists in TGLMs.
  arXiv  Detail & Related papers  (2025-05-19T06:25:33Z)
• ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning [31.629956388962814]
  ScaDyG is a time-aware scalable learning paradigm for dynamic graph networks.<n> experiments on 12 datasets demonstrate that ScaDyG performs comparably well or even outperforms other SOTA methods in both node and link-level downstream tasks.
  arXiv  Detail & Related papers  (2025-01-27T12:39:16Z)
• T-Graphormer: Using Transformers for Spatiotemporal Forecasting [2.855856661274715]
  T-Graphormer reduces root mean squared error (RMSE) and mean absolute percentage error (MAPE) by up to 20% and 10%.<n>We show the effectiveness of T-Graphormer on real-world traffic prediction benchmark datasets.
  arXiv  Detail & Related papers  (2025-01-22T23:32:29Z)
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning [131.04781590452308]
  We present SimTeG, a frustratingly Simple approach for Textual Graph learning. We first perform supervised parameter-efficient fine-tuning (PEFT) on a pre-trained LM on the downstream task. We then generate node embeddings using the last hidden states of finetuned LM.
  arXiv  Detail & Related papers  (2023-08-03T07:00:04Z)
• Temporal Graph Benchmark for Machine Learning on Temporal Graphs [54.52243310226456]
  Temporal Graph Benchmark (TGB) is a collection of challenging and diverse benchmark datasets. We benchmark each dataset and find that the performance of common models can vary drastically across datasets. TGB provides an automated machine learning pipeline for reproducible and accessible temporal graph research.
  arXiv  Detail & Related papers  (2023-07-03T13:58:20Z)
• Towards Better Dynamic Graph Learning: New Architecture and Unified Library [29.625205125350313]
  DyGFormer is a Transformer-based architecture for dynamic graph learning. DyGLib is a unified library with standard training pipelines and coding interfaces.
  arXiv  Detail & Related papers  (2023-03-23T05:27:32Z)
• Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling [2.3022070933226217]
  We propose a novel framework, namely static- and dynamic-graph learning-neural network (GL) The model acquires static and dynamic graph matrices from data to model long-term and short-term patterns respectively. It achieves state-of-the-art performance on almost all datasets.
  arXiv  Detail & Related papers  (2021-12-06T08:19:15Z)
• Multivariate Time Series Classification with Hierarchical Variational Graph Pooling [23.66868187446734]
  Existing deep learning-based MTSC techniques are primarily concerned with the temporal dependency of single time series. We propose a novel graph pooling-based framework MTPool to obtain the expressive global representation of MTS. Experiments on ten benchmark datasets exhibit MTPool outperforms state-of-the-art strategies in the MTSC task.
  arXiv  Detail & Related papers  (2020-10-12T12:36:47Z)

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.