# UniDyG: A Unified and Effective Representation Learning Approach for Large Dynamic Graphs arXiv: https://arxiv.org/abs/2502.16431 ยท HTML: https://mlsanity.com/paper/2502.16431/ ## Key facts - Cited by 3 papers in the map (data through 14 Oct 2026). - Builds on 36 of its 66 references that are in the map. - First posted on arXiv 23 Feb 2025. ## Builds on (most cited first, 30 of 36) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021) - [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022) - [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020) - [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020) - [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017) - [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019) - [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019) - [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016) - [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) - [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https://mlsanity.com/paper/2311.06184/) (2023) - [Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring](https://mlsanity.com/paper/2211.12250/) (2022) - [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023) - [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) - [Motifs in Temporal Networks](https://mlsanity.com/paper/1612.09259/) (2016) - [APAN: Asynchronous Propagation Attention Network for Real-time Temporal Graph Embedding](https://mlsanity.com/paper/2011.11545/) (2020) - [TSLANet: Rethinking Transformers for Time Series Representation Learning](https://mlsanity.com/paper/2404.08472/) (2024) - [Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space](https://mlsanity.com/paper/2107.03767/) (2021) - [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022) - [Anomaly Detection in Dynamic Graphs via Transformer](https://mlsanity.com/paper/2106.09876/) (2021) - [Provably expressive temporal graph networks](https://mlsanity.com/paper/2209.15059/) (2022) - [Neighborhood-aware Scalable Temporal Network Representation Learning](https://mlsanity.com/paper/2209.01084/) (2022) - [Attributed Network Embedding for Learning in a Dynamic Environment](https://mlsanity.com/paper/1706.01860/) (2017) - [DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs](https://mlsanity.com/paper/2406.12072/) (2024) - [Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks](https://mlsanity.com/paper/2208.10364/) (2022) - [DyTed: Disentangled Representation Learning for Discrete-time Dynamic Graph](https://mlsanity.com/paper/2210.10592/) (2022) - [DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data](https://mlsanity.com/paper/2107.02168/) (2021) - [HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Prediction](https://mlsanity.com/paper/2304.07302/) (2023) ## Built on by (most cited first, 3 of 3) - [Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models](https://mlsanity.com/paper/2503.14411/) (2025) - [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026) - [Global-Lens Transformers: Adaptive Token Mixing for Dynamic Link Prediction](https://mlsanity.com/paper/2511.12442/) (2025) ## Abstract (arXiv) Dynamic graphs are formulated in continuous-time or discrete-time dynamic graphs. They differ in temporal granularity: Continuous-Time Dynamic Graphs (CTDGs) exhibit rapid, localized changes, while Discrete-Time Dynamic Graphs (DTDGs) show gradual, global updates. This difference leads to isolated developments in representation learning for each type. To advance representation learning, recent research attempts to design a unified model capable of handling both CTDGs and DTDGs. However, it typically focuses on local dynamic propagation for temporal structure learning in the time domain, failing to accurately capture the structural evolution associated with each temporal granularity. In addition, existing works-whether specific or unified-often overlook the issue of temporal noise, compromising the model robustness and effectiveness. To better model both types of dynamic graphs, we propose UniDyG, a unified and effective representation learning approach, which scales to large dynamic graphs. We first propose a novel Fourier Graph Attention (FGAT) mechanism that can model local and global structural correlations based on recent neighbors and complex-number selective aggregation, while theoretically ensuring consistent representations of dynamic graphs over time. Based on approximation theory, we demonstrate that FGAT is well-suited to capture the underlying structures in CTDGs and DTDGs. We further enhance FGAT to resist temporal noise by designing an energy-gated unit, which adaptively filters out high-frequency noise according to the energy. Last, we leverage our FGAT mechanisms for temporal structure learning and employ the frequency-enhanced linear function for node-level dynamic updates, facilitating the generation of high-quality temporal embeddings. Extensive experiments show that our UniDyG achieves an average improvement of 14.4% over sixteen baselines across nine dynamic graphs.