# GA-DRL: Graph Neural Network-Augmented Deep Reinforcement Learning for DAG Task Scheduling over Dynamic Vehicular Clouds

arXiv: https://arxiv.org/abs/2307.00777 · HTML: https://mlsanity.com/paper/2307.00777/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 60 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation](https://mlsanity.com/paper/2101.00787/) (2021)
- [Fast Adaptive Task Offloading in Edge Computing based on Meta Reinforcement Learning](https://mlsanity.com/paper/2008.02033/) (2020)
- [Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization](https://mlsanity.com/paper/2010.05244/) (2020)
- [Offloading and Resource Allocation with General Task Graph in Mobile Edge Computing: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/2002.08119/) (2020)
- [A Distributed Deep Reinforcement Learning Technique for Application Placement in Edge and Fog Computing Environments](https://mlsanity.com/paper/2110.12415/) (2021)
- [RFID: Towards Low Latency and Reliable DAG Task Scheduling over Dynamic Vehicular Clouds](https://mlsanity.com/paper/2208.12568/) (2022)
- [Path Loss Models for V2V mmWave Communication: Performance Evaluation and Open Challenges](https://mlsanity.com/paper/1907.10126/) (2019)
- [Energy-Aware Graph Task Scheduling in Software-Defined Air-Ground Integrated Vehicular Networks](https://mlsanity.com/paper/2008.01144/) (2020)

## Built on by (most cited first, 10 of 10)

- [DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach](https://mlsanity.com/paper/2406.06986/) (2024)
- [Graph Neural Networks for Job Shop Scheduling Problems: A Survey](https://mlsanity.com/paper/2406.14096/) (2024)
- [Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review](https://mlsanity.com/paper/2501.01007/) (2025)
- [Deep Reinforcement Learning based Autonomous Decision-Making for Cooperative UAVs: A Search and Rescue Real World Application](https://mlsanity.com/paper/2502.20326/) (2025)
- [Two-Timescale Model Caching and Resource Allocation for Edge-Enabled AI-Generated Content Services](https://mlsanity.com/paper/2411.01458/) (2024)
- [Optimizing Age of Information in Vehicular Edge Computing with Federated Graph Neural Network Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2407.02342/) (2024)
- [SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling](https://mlsanity.com/paper/2606.06820/) (2026)
- [PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End Computing](https://mlsanity.com/paper/2609.03503/) (2026)
- [Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2609.14952/) (2026)
- [HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud](https://mlsanity.com/paper/2609.14968/) (2026)

## Abstract (arXiv)

Vehicular clouds (VCs) are modern platforms for processing of computation-intensive tasks over vehicles. Such tasks are often represented as directed acyclic graphs (DAGs) consisting of interdependent vertices/subtasks and directed edges. In this paper, we propose a graph neural network-augmented deep reinforcement learning scheme (GA-DRL) for scheduling DAG tasks over dynamic VCs. In doing so, we first model the VC-assisted DAG task scheduling as a Markov decision process. We then adopt a multi-head graph attention network (GAT) to extract the features of DAG subtasks. Our developed GAT enables a two-way aggregation of the topological information in a DAG task by simultaneously considering predecessors and successors of each subtask. We further introduce non-uniform DAG neighborhood sampling through codifying the scheduling priority of different subtasks, which makes our developed GAT generalizable to completely unseen DAG task topologies. Finally, we augment GAT into a double deep Q-network learning module to conduct subtask-to-vehicle assignment according to the extracted features of subtasks, while considering the dynamics and heterogeneity of the vehicles in VCs. Through simulating various DAG tasks under real-world movement traces of vehicles, we demonstrate that GA-DRL outperforms existing benchmarks in terms of DAG task completion time.