# Task Placement and Resource Allocation for Edge Machine Learning: A GNN-based Multi-Agent Reinforcement Learning Paradigm

arXiv: https://arxiv.org/abs/2302.00571 · HTML: https://mlsanity.com/paper/2302.00571/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2023.

## Built on by (most cited first, 7 of 7)

- [Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement](https://mlsanity.com/paper/2508.12851/) (2025)
- [Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review](https://mlsanity.com/paper/2501.01007/) (2025)
- [Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approach](https://mlsanity.com/paper/2505.12902/) (2025)
- [Topology Enhanced MARL for Multi-Agent Cooperative Decision-Making of CAVs](https://mlsanity.com/paper/2507.12110/) (2025)
- [A Framework for dynamically meeting performance objectives on a service mesh](https://mlsanity.com/paper/2306.14178/) (2023)
- [Dynamic Pricing for On-Demand DNN Inference in the Edge-AI Market](https://mlsanity.com/paper/2503.04521/) (2025)
- [TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs](https://mlsanity.com/paper/2602.18109/) (2026)

## Abstract (arXiv)

Machine learning (ML) tasks are one of the major workloads in today's edge computing networks. Existing edge-cloud schedulers allocate the requested amounts of resources to each task, falling short of best utilizing the limited edge resources for ML tasks. This paper proposes TapFinger, a distributed scheduler for edge clusters that minimizes the total completion time of ML tasks through co-optimizing task placement and fine-grained multi-resource allocation. To learn the tasks' uncertain resource sensitivity and enable distributed scheduling, we adopt multi-agent reinforcement learning (MARL) and propose several techniques to make it efficient, including a heterogeneous graph attention network as the MARL backbone, a tailored task selection phase in the actor network, and the integration of Bayes' theorem and masking schemes. We first implement a single-task scheduling version, which schedules at most one task each time. Then we generalize to the multi-task scheduling case, in which a sequence of tasks is scheduled simultaneously. Our design can mitigate the expanded decision space and yield fast convergence to optimal scheduling solutions. Extensive experiments using synthetic and test-bed ML task traces show that TapFinger can achieve up to 54.9% reduction in the average task completion time and improve resource efficiency as compared to state-of-the-art schedulers.