DECAF: Learning to be Fair in Multi-agent Resource Allocation

• URL: http://arxiv.org/abs/2502.04281v1
• Date: Thu, 06 Feb 2025 18:29:11 GMT
• Title: DECAF: Learning to be Fair in Multi-agent Resource Allocation
• Authors: Ashwin Kumar, William Yeoh,
• Abstract summary: We propose methods to learn fair and efficient policies in centralized resource allocation. Our methods are applied to learning long-term fairness in a novel and general framework for fairness in multi-agent systems.
• Score: 4.788163807490197
• License:
• Abstract: A wide variety of resource allocation problems operate under resource constraints that are managed by a central arbitrator, with agents who evaluate and communicate preferences over these resources. We formulate this broad class of problems as Distributed Evaluation, Centralized Allocation (DECA) problems and propose methods to learn fair and efficient policies in centralized resource allocation. Our methods are applied to learning long-term fairness in a novel and general framework for fairness in multi-agent systems. We show three different methods based on Double Deep Q-Learning: (1) A joint weighted optimization of fairness and utility, (2) a split optimization, learning two separate Q-estimators for utility and fairness, and (3) an online policy perturbation to guide existing black-box utility functions toward fair solutions. Our methods outperform existing fair MARL approaches on multiple resource allocation domains, even when evaluated using diverse fairness functions, and allow for flexible online trade-offs between utility and fairness.

Related papers

• Active Learning for Fair and Stable Online Allocations [6.23798328186465]
  We consider feedback from a select subset of agents at each epoch of the online resource allocation process. Our algorithms provide regret bounds that are sub-linear in number of time-periods for various measures. We show that efficient decision-making does not require extensive feedback and produces efficient outcomes for a variety of problem classes.
  arXiv  Detail & Related papers  (2024-06-20T23:23:23Z)
• Semi-Supervised Learning Approach for Efficient Resource Allocation with Network Slicing in O-RAN [5.1435595246496595]
  This paper introduces an innovative approach to the resource allocation problem. It aims to coordinate multiple independent x-applications (xAPPs) for network slicing and resource allocation in the Open Radio Access Network (O-RAN)
  arXiv  Detail & Related papers  (2024-01-16T22:23:27Z)
• Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning [30.605881670761853]
  We propose a Reinforcement Learning approach to achieve fairness in finite-horizon episodic MDPs. We show that such an approach achieves sub-linear regret in terms of the number of episodes.
  arXiv  Detail & Related papers  (2023-06-01T03:43:53Z)
• How Robust is Your Fairness? Evaluating and Sustaining Fairness under Unseen Distribution Shifts [107.72786199113183]
  We propose a novel fairness learning method termed CUrvature MAtching (CUMA) CUMA achieves robust fairness generalizable to unseen domains with unknown distributional shifts. We evaluate our method on three popular fairness datasets.
  arXiv  Detail & Related papers  (2022-07-04T02:37:50Z)
• Multi-Fair Pareto Boosting [7.824964622317634]
  We introduce a new fairness notion,Multi-Max Mistreatment(MMM), which measures unfairness while considering both (multi-attribute) protected group and class membership of instances. We solve the problem using a boosting approach that in-training,incorporates multi-fairness treatment in the distribution update and post-training.
  arXiv  Detail & Related papers  (2021-04-27T16:37:35Z)
• Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning [12.215625537879108]
  We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL) We propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness.
  arXiv  Detail & Related papers  (2020-12-17T07:17:36Z)
• Toward Multiple Federated Learning Services Resource Sharing in Mobile Edge Networks [88.15736037284408]
  We study a new model of multiple federated learning services at the multi-access edge computing server. We propose a joint resource optimization and hyper-learning rate control problem, namely MS-FEDL. Our simulation results demonstrate the convergence performance of our proposed algorithms.
  arXiv  Detail & Related papers  (2020-11-25T01:29:41Z)
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [61.317911756566126]
  We propose a Towards Fair Knowledge Transfer framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain mixup generation is exploited to augment the minority source set with target information to enhance fairness. Our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.
  arXiv  Detail & Related papers  (2020-10-23T06:29:09Z)
• Resource Allocation via Model-Free Deep Learning in Free Space Optical Communications [119.81868223344173]
  The paper investigates the general problem of resource allocation for mitigating channel fading effects in Free Space Optical (FSO) communications. Under this framework, we propose two algorithms that solve FSO resource allocation problems.
  arXiv  Detail & Related papers  (2020-07-27T17:38:51Z)
• F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning [110.35516334788687]
  Decentralized multi-agent reinforcement learning algorithms are sometimes unpractical in complicated applications. We propose a flexible fully decentralized actor-critic MARL framework, which can handle large-scale general cooperative multi-agent setting. Our framework can achieve scalability and stability for large-scale environment and reduce information transmission.
  arXiv  Detail & Related papers  (2020-04-17T14:56:29Z)
• Universal Source-Free Domain Adaptation [57.37520645827318]
  We propose a novel two-stage learning process for domain adaptation. In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift. In the Deployment stage, the goal is to design a unified adaptation algorithm capable of operating across a wide range of category-gaps.
  arXiv  Detail & Related papers  (2020-04-09T07:26:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.