# Dynamic Graph Representation Learning via Self-Attention Networks

arXiv: https://arxiv.org/abs/1812.09430 · HTML: https://mlsanity.com/paper/1812.09430/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2018.

## Built on by (most cited first, 30 of 39)

- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [A Survey on Embedding Dynamic Graphs](https://mlsanity.com/paper/2101.01229/) (2021)
- [Dynamic Network Embedding Survey](https://mlsanity.com/paper/2103.15447/) (2021)
- [NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics](https://mlsanity.com/paper/2306.06202/) (2023)
- [Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review](https://mlsanity.com/paper/2303.06471/) (2023)
- [FeatureNorm: L2 Feature Normalization for Dynamic Graph Embedding](https://mlsanity.com/paper/2103.00164/) (2021)
- [Anomaly Detection in Dynamic Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2406.00134/) (2024)
- [GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs](https://mlsanity.com/paper/2110.05598/) (2021)
- [Pre-Training on Dynamic Graph Neural Networks](https://mlsanity.com/paper/2102.12380/) (2021)
- [DynSTGAT: Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control](https://mlsanity.com/paper/2109.05491/) (2021)
- [An Empirical Study: Extensive Deep Temporal Point Process](https://mlsanity.com/paper/2110.09823/) (2021)
- [A Mutually Exciting Latent Space Hawkes Process Model for Continuous-time Networks](https://mlsanity.com/paper/2205.09263/) (2022)
- [Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2308.10779/) (2023)
- [Explaining Dynamic Graph Neural Networks via Relevance Back-propagation](https://mlsanity.com/paper/2207.11175/) (2022)
- [DyGCN: Dynamic Graph Embedding with Graph Convolutional Network](https://mlsanity.com/paper/2104.02962/) (2021)
- [Bi-Level Attention Graph Neural Networks](https://mlsanity.com/paper/2304.11533/) (2023)
- [DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability](https://mlsanity.com/paper/2111.10447/) (2021)
- [A Primer on Temporal Graph Learning](https://mlsanity.com/paper/2401.03988/) (2024)
- [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://mlsanity.com/paper/2402.00299/) (2024)
- [Reasoning over Multi-view Knowledge Graphs](https://mlsanity.com/paper/2209.13702/) (2022)
- [Lightweight Compositional Embeddings for Incremental Streaming Recommendation](https://mlsanity.com/paper/2202.02427/) (2022)
- [AoI-based Temporal Attention Graph Neural Network for Popularity Prediction and Content Caching](https://mlsanity.com/paper/2208.08606/) (2022)
- [Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs](https://mlsanity.com/paper/2311.01647/) (2023)
- [Exploring Time Granularity on Temporal Graphs for Dynamic Link Prediction in Real-world Networks](https://mlsanity.com/paper/2311.12255/) (2023)
- [BrainMAP: Learning Multiple Activation Pathways in Brain Networks](https://mlsanity.com/paper/2412.17404/) (2024)
- [ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding](https://mlsanity.com/paper/2310.04865/) (2023)
- [Curriculum Negative Mining For Temporal Networks](https://mlsanity.com/paper/2407.17070/) (2024)
- [Predicting travel demand of a bike sharing system using graph convolutional neural networks](https://mlsanity.com/paper/2408.09317/) (2024)
- [Attention-based graph neural networks: a survey](https://mlsanity.com/paper/2605.08679/) (2026)
- [Sparsity-aware neural user behavior modeling in online interaction platforms](https://mlsanity.com/paper/2202.13491/) (2022)

## Abstract (arXiv)

Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evolve over time. In this paper, we present Dynamic Self-Attention Network (DySAT), a novel neural architecture that operates on dynamic graphs and learns node representations that capture both structural properties and temporal evolutionary patterns. Specifically, DySAT computes node representations by jointly employing self-attention layers along two dimensions: structural neighborhood and temporal dynamics. We conduct link prediction experiments on two classes of graphs: communication networks and bipartite rating networks. Our experimental results show that DySAT has a significant performance gain over several different state-of-the-art graph embedding baselines.