# TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer

arXiv: https://arxiv.org/abs/2506.00431 · HTML: https://mlsanity.com/paper/2506.00431/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 31 May 2025.

## Builds on (most cited first, 23 of 23)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Representation Learning for Dynamic Graphs: A Survey](https://mlsanity.com/paper/1905.11485/) (2019)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs](https://mlsanity.com/paper/1705.05742/) (2017)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [ROLAND: Graph Learning Framework for Dynamic Graphs](https://mlsanity.com/paper/2208.07239/) (2022)
- [Dynamic Graph Convolutional Networks](https://mlsanity.com/paper/1704.06199/) (2017)
- [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020)
- [Session-based Social Recommendation via Dynamic Graph Attention Networks](https://mlsanity.com/paper/1902.09362/) (2019)
- [Dynamic Graph Neural Networks for Sequential Recommendation](https://mlsanity.com/paper/2104.07368/) (2021)
- [Evolutionary dynamics of higher-order interactions in social networks](https://mlsanity.com/paper/2001.10313/) (2020)
- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [On the Feasibility of Simple Transformer for Dynamic Graph Modeling](https://mlsanity.com/paper/2401.14009/) (2024)
- [Improving Temporal Link Prediction via Temporal Walk Matrix Projection](https://mlsanity.com/paper/2410.04013/) (2024)
- [Efficient Neural Common Neighbor for Temporal Graph Link Prediction](https://mlsanity.com/paper/2406.07926/) (2024)
- [Repeat-Aware Neighbor Sampling for Dynamic Graph Learning](https://mlsanity.com/paper/2405.17473/) (2024)
- [Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs](https://mlsanity.com/paper/2003.13432/) (2020)
- [Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks](https://mlsanity.com/paper/2408.03669/) (2024)

## Built on by (most cited first, 5 of 5)

- [Temporal Graph Pattern Machine](https://mlsanity.com/paper/2601.22454/) (2026)
- [GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning](https://mlsanity.com/paper/2507.03267/) (2025)
- [Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution](https://mlsanity.com/paper/2603.13360/) (2026)
- [MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning](https://mlsanity.com/paper/2511.11837/) (2025)
- [Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix](https://mlsanity.com/paper/2605.16112/) (2026)

## Abstract (arXiv)

Due to the proficiency of self-attention mechanisms (SAMs) in capturing dependencies in sequence modeling, several existing dynamic graph neural networks (DGNNs) utilize Transformer architectures with various encoding designs to capture sequential evolutions of dynamic graphs. However, the effectiveness and efficiency of these Transformer-based DGNNs vary significantly, highlighting the importance of properly defining the SAM on dynamic graphs and comprehensively encoding temporal and interactive dynamics without extra complex modules. In this work, we propose TIDFormer, a dynamic graph TransFormer that fully exploits Temporal and Interactive Dynamics in an efficient manner. We clarify and verify the interpretability of our proposed SAM, addressing the open problem of its uninterpretable definitions on dynamic graphs in previous works. To model the temporal and interactive dynamics, respectively, we utilize the calendar-based time partitioning information and extract informative interaction embeddings for both bipartite and non-bipartite graphs using merely the sampled first-order neighbors. In addition, we jointly model temporal and interactive features by capturing potential changes in historical interaction patterns through a simple decomposition. We conduct extensive experiments on several dynamic graph datasets to verify the effectiveness and efficiency of TIDFormer. The experimental results demonstrate that TIDFormer excels, outperforming state-of-the-art models across most datasets and experimental settings. Furthermore, TIDFormer exhibits significant efficiency advantages compared to previous Transformer-based methods.