# HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud

arXiv: https://arxiv.org/abs/2609.14968 · HTML: https://mlsanity.com/paper/2609.14968/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 8 of its 36 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 8 of 8)

- [Learning Scheduling Algorithms for Data Processing Clusters](https://mlsanity.com/paper/1810.01963/) (2018)
- [Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications](https://mlsanity.com/paper/2206.07922/) (2022)
- [Reinforcement learning on graphs: A survey](https://mlsanity.com/paper/2204.06127/) (2022)
- [GA-DRL: Graph Neural Network-Augmented Deep Reinforcement Learning for DAG Task Scheduling over Dynamic Vehicular Clouds](https://mlsanity.com/paper/2307.00777/) (2023)
- [OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters](https://mlsanity.com/paper/2503.17469/) (2025)
- [Cost-Aware Dynamic Cloud Workflow Scheduling using Self-Attention and Evolutionary Reinforcement Learning](https://mlsanity.com/paper/2409.18444/) (2024)
- [H2O-Cloud: A Resource and Quality of Service-Aware Task Scheduling Framework for Warehouse-Scale Data Centers -- A Hierarchical Hybrid DRL (Deep Reinforcement Learning) based Approach](https://mlsanity.com/paper/1912.10808/) (2019)
- [An Improved Scheduling with Advantage Actor-Critic for Storm Workloads](https://mlsanity.com/paper/2312.04126/) (2023)

## Abstract (arXiv)

Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay between DAG topologies and multi-dimensional resource constraints. While DRL has shown promise, existing GNN-based approaches often struggle to efficiently model high-order topological dependencies and suffer from loose coupling between task and resource states, leading to myopic scheduling decisions. To address these limitations, we propose HiGFRL, a Hierarchical Graph Fusion-Driven Reinforcement Learning framework. HiGFRL constructs a novel three-level state representation comprising a Static Hypergraph, a Dynamic Global Graph, and a Local Bipartite Graph to explicitly model the interplay between task dependencies and real-time cluster dynamics. Specifically, we design a fusion-driven dual-network architecture to optimize RL decision-making, where a Context Fusion Allocator integrates local bipartite matching features with fused global context to execute precise task-to-node allocation, and a Global State Evaluator leverages the global dynamic graph representation to accurately estimate expected long-term cumulative reward. Furthermore, we incorporate a topology-prior-guided hybrid reward mechanism that distills static topological priors into the learning process to accelerate convergence. Extensive experiments using real-world Alibaba cluster traces demonstrate that HiGFRL significantly outperforms heuristics and DRL baselines. Specifically, in challenging large-scale high-load scenarios, HiGFRL reduces the Makespan by up to 32.55%, and optimizes the average task flow time and average task wait time by 13.58% and 13.79%, respectively. Experimental results confirm that HiGFRL not only significantly improves cluster throughput but also ensures superior QoS by substantially reducing queuing delays. Code Release:https://github.com/igeng/HiGFRL.