# Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction

arXiv: https://arxiv.org/abs/2106.07161 · HTML: https://mlsanity.com/paper/2106.07161/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2021.

## Built on by (most cited first, 17 of 17)

- [GOHOME: Graph-Oriented Heatmap Output for future Motion Estimation](https://mlsanity.com/paper/2109.01827/) (2021)
- [HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding](https://mlsanity.com/paper/2205.09753/) (2022)
- [PyG 2.0: Scalable Learning on Real World Graphs](https://mlsanity.com/paper/2507.16991/) (2025)
- [Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding](https://mlsanity.com/paper/2310.12970/) (2023)
- [Modeling Dynamic Environments with Scene Graph Memory](https://mlsanity.com/paper/2305.17537/) (2023)
- [Unified Spatial-Temporal Edge-Enhanced Graph Networks for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2502.02504/) (2025)
- [Holistic Graph-based Motion Prediction](https://mlsanity.com/paper/2301.13545/) (2023)
- [Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction](https://mlsanity.com/paper/2505.06856/) (2025)
- [Deep Surrogate Docking: Accelerating Automated Drug Discovery with Graph Neural Networks](https://mlsanity.com/paper/2211.02720/) (2022)
- [Predictive AI with External Knowledge Infusion: Datasets and Benchmarks for Stock Markets](https://mlsanity.com/paper/2504.20058/) (2025)
- [NashFormer: Leveraging Local Nash Equilibria for Semantically Diverse Trajectory Prediction](https://mlsanity.com/paper/2305.17600/) (2023)
- [H2G2-Net: A Hierarchical Heterogeneous Graph Generative Network Framework for Discovery of Multi-Modal Physiological Responses](https://mlsanity.com/paper/2401.02905/) (2024)
- [Performance Prediction of Hub-Based Swarms](https://mlsanity.com/paper/2408.04822/) (2024)
- [Beyond Scanpaths: Graph-Based Gaze Simulation in Dynamic Scenes](https://mlsanity.com/paper/2603.28319/) (2026)
- [Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids](https://mlsanity.com/paper/2605.23194/) (2026)
- [hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freeways](https://mlsanity.com/paper/2606.27577/) (2026)
- [STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot Interaction](https://mlsanity.com/paper/2609.40245/) (2026)

## Abstract (arXiv)

Simultaneous trajectory prediction for multiple heterogeneous traffic participants is essential for the safe and efficient operation of connected automated vehicles under complex driving situations in the real world. The multi-agent prediction task is challenging, as the motions of traffic participants are affected by many factors, including their individual dynamics, their interactions with surrounding agents, the traffic infrastructures, and the number and modalities of the target agents. To further advance the trajectory prediction techniques, in this work we propose a three-channel framework together with a novel Heterogeneous Edge-enhanced graph ATtention network (HEAT), which is able to deal with the heterogeneity of the target agents and traffic participants involved. Specifically, the agent's dynamics are extracted from their historical states using type-specific encoders. The inter-agent interactions are represented with a directed edge-featured heterogeneous graph, and then interaction features are extracted using the proposed HEAT network. Besides, the map features are shared across all agents by introducing a selective gate mechanism. And finally, the trajectories of multi-agent are executed simultaneously. Validations using both urban and highway driving datasets show that the proposed model can realize simultaneous trajectory predictions for multiple agents under complex traffic situations, and achieve state-of-the-art performance with respect to prediction accuracy, demonstrating its feasibility and effectiveness.