Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing

Yong Zhao, Zhengqiu Zhu, Chen Gao, En Wang, Jincai Huang, Fei-Yue Wang

TL;DR

This paper formally defines and addresses this Dependency-aware Multi-task Allocation (DMA) problem and proposes a novel framework, termed Heterogeneous Graph Reinforcement Learning for Task Allocation (HGRL-TA), to derive optimal allocation policies.

Abstract

Spatial Crowdsourcing (SC) is gaining traction in both academia and industry, with tasks on SC platforms becoming increasingly complex and requiring collaboration among workers with diverse skills. Recent research works address complex tasks by dividing them into subtasks with dependencies and assigning them to suitable workers. However, the dependencies among subtasks and their heterogeneous skill requirements, as well as the need for efficient utilization of workers' limited work time in the multi-task allocation mode, pose challenges in achieving an optimal task allocation scheme. Therefore, this paper formally investigates the problem of Dependency-aware Multi-task Allocation (DMA) and presents a well-designed framework to solve it, known as Heterogeneous Graph Reinforcement Learning-based Task Allocation (HGRL-TA). To address the challenges associated with representing and embedding diverse problem instances to ensure robust generalization, we propose a multi-relation graph model and a Compound-path-based Heterogeneous Graph Attention Network (CHANet) for effectively representing and capturing intricate relations among tasks and workers, as well as providing embedding of problem state. The task allocation decision is determined sequentially by a policy network, which undergoes simultaneous training with CHANet using the proximal policy optimization algorithm. Extensive experiment results demonstrate the effectiveness and generality of the proposed HGRL-TA in solving the DMA problem, leading to average profits that is 21.78% higher than those achieved using the metaheuristic methods.

Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing

TL;DR

This paper formally defines and addresses this Dependency-aware Multi-task Allocation (DMA) problem and proposes a novel framework, termed Heterogeneous Graph Reinforcement Learning for Task Allocation (HGRL-TA), to derive optimal allocation policies.

Abstract

Spatial Crowdsourcing (SC) is gaining traction in both academia and industry, with tasks on SC platforms becoming increasingly complex and requiring collaboration among workers with diverse skills. Recent research works address complex tasks by dividing them into subtasks with dependencies and assigning them to suitable workers. However, the dependencies among subtasks and their heterogeneous skill requirements, as well as the need for efficient utilization of workers' limited work time in the multi-task allocation mode, pose challenges in achieving an optimal task allocation scheme. Therefore, this paper formally investigates the problem of Dependency-aware Multi-task Allocation (DMA) and presents a well-designed framework to solve it, known as Heterogeneous Graph Reinforcement Learning-based Task Allocation (HGRL-TA). To address the challenges associated with representing and embedding diverse problem instances to ensure robust generalization, we propose a multi-relation graph model and a Compound-path-based Heterogeneous Graph Attention Network (CHANet) for effectively representing and capturing intricate relations among tasks and workers, as well as providing embedding of problem state. The task allocation decision is determined sequentially by a policy network, which undergoes simultaneous training with CHANet using the proximal policy optimization algorithm. Extensive experiment results demonstrate the effectiveness and generality of the proposed HGRL-TA in solving the DMA problem, leading to average profits that is 21.78% higher than those achieved using the metaheuristic methods.

Paper Structure

This paper contains 32 sections, 19 equations, 13 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Works
  3. Task Allocation in Spatial Crowdsourcing
  4. Graph Reinforcement Learning for Spatial Crowdsourcing
  5. System Model and Problem Formulation
  6. System Model
  7. Problem Formulation
  8. Illustrative Instance
  9. Methodology
  10. Heterogeneous Graph Reinforcement Learning-based Task Allocation
  11. Multi-relation Graph
  12. Edge representation
  13. Node representation
  14. Graph Update
  15. Compound-based Heterogeneous Graph Attention Network
  16. ...and 17 more sections

Figures (13)

  • Figure 1: The diagram of related definitional items in this paper.
  • Figure 2: An illustrative instance of the DMA problem.
  • Figure 3: Overview of the proposed HGRL-TA.
  • Figure 4: The illustration of the meta-path-based method and proposed compound-path-based method.
  • Figure 5: The architecture of CHANet.
  • ...and 8 more figures