Agent-oriented Joint Decision Support for Data Owners in Auction-based Federated Learning

• URL: http://arxiv.org/abs/2405.05991v1
• Date: Thu, 9 May 2024 02:35:46 GMT
• Title: Agent-oriented Joint Decision Support for Data Owners in Auction-based Federated Learning
• Authors: Xiaoli Tang, Han Yu, Xiaoxiao Li,
• Abstract summary: Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners (DOs) to join FL through economic means. We propose a first-of-its-kind agent-oriented joint Pricing, Acceptance and Sub-delegation decision support approach for data owners in AFL (PAS-AFL) It is the first to enable each DO to take on multiple FL tasks simultaneously to earn higher income for DOs and enhance the throughput of FL tasks in the AFL ecosystem.
• Score: 32.6997332038178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners (DOs) to join FL through economic means. While many existing AFL methods focus on providing decision support to model users (MUs) and the AFL auctioneer, decision support for data owners remains open. To bridge this gap, we propose a first-of-its-kind agent-oriented joint Pricing, Acceptance and Sub-delegation decision support approach for data owners in AFL (PAS-AFL). By considering a DO's current reputation, pending FL tasks, willingness to train FL models, and its trust relationships with other DOs, it provides a systematic approach for a DO to make joint decisions on AFL bid acceptance, task sub-delegation and pricing based on Lyapunov optimization to maximize its utility. It is the first to enable each DO to take on multiple FL tasks simultaneously to earn higher income for DOs and enhance the throughput of FL tasks in the AFL ecosystem. Extensive experiments based on six benchmarking datasets demonstrate significant advantages of PAS-AFL compared to six alternative strategies, beating the best baseline by 28.77% and 2.64% on average in terms of utility and test accuracy of the resulting FL models, respectively.

Related papers

• Intelligent Agents for Auction-based Federated Learning: A Survey [41.4320233892375]
  Auction-based federated learning (AFL) is an emerging category of FL incentive mechanism design. We provide a first-of-its-kind survey on the Intelligent Agents for AFL (IA-AFL) literature.
  arXiv  Detail & Related papers  (2024-04-20T03:05:25Z)
• A Bargaining-based Approach for Feature Trading in Vertical Federated Learning [54.51890573369637]
  We propose a bargaining-based feature trading approach in Vertical Federated Learning (VFL) to encourage economically efficient transactions. Our model incorporates performance gain-based pricing, taking into account the revenue-based optimization objectives of both parties.
  arXiv  Detail & Related papers  (2024-02-23T10:21:07Z)
• Multi-Session Budget Optimization for Forward Auction-based Federated Learning [17.546044136396468]
  Auction-based Federated Learning (AFL) has emerged as an important research field in recent years. We propose the Multi-session Budget Optimization Strategy for forward Auction-based Federated Learning (MultiBOS-AFL) Based on hierarchical reinforcement learning, MultiBOS-AFL jointly optimize inter-session budget pacing and intra-session bidding for AFL MUs.
  arXiv  Detail & Related papers  (2023-11-21T11:57:41Z)
• Hire When You Need to: Gradual Participant Recruitment for Auction-based Federated Learning [16.83897148104]
  We propose a Gradual Participant Selection scheme for Federated Learning (GPS-AFL) GPS-AFL gradually selects the required DOs over multiple rounds of training as more information is revealed through repeated interactions. It is designed to strike a balance between cost saving and performance enhancement, while mitigating the drawbacks of selection bias in reputation-based FL.
  arXiv  Detail & Related papers  (2023-10-04T08:19:04Z)
• Utility-Maximizing Bidding Strategy for Data Consumers in Auction-based Federated Learning [14.410324763825733]
  Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners to join FL through economic means. This paper proposes a first-of-its-kind utility-maximizing bidding strategy for data consumers in federated learning (Fed-Bidder)
  arXiv  Detail & Related papers  (2023-05-11T13:16:36Z)
• VFed-SSD: Towards Practical Vertical Federated Advertising [53.08038962443853]
  We propose a semi-supervised split distillation framework VFed-SSD to alleviate the two limitations. Specifically, we develop a self-supervised task MatchedPair Detection (MPD) to exploit the vertically partitioned unlabeled data. Our framework provides an efficient federation-enhanced solution for real-time display advertising with minimal deploying cost and significant performance lift.
  arXiv  Detail & Related papers  (2022-05-31T17:45:30Z)
• Towards Fairness-Aware Federated Learning [19.73772410934193]
  We propose a taxonomy of Fairness-Aware Federated Learning (FAFL) approaches covering major steps in Federated Learning. We discuss the main metrics for experimentally evaluating the performance of FAFL approaches.
  arXiv  Detail & Related papers  (2021-11-02T20:20:28Z)
• A Contract Theory based Incentive Mechanism for Federated Learning [52.24418084256517]
  Federated learning (FL) serves as a data privacy-preserved machine learning paradigm, and realizes the collaborative model trained by distributed clients. To accomplish an FL task, the task publisher needs to pay financial incentives to the FL server and FL server offloads the task to the contributing FL clients. It is challenging to design proper incentives for the FL clients due to the fact that the task is privately trained by the clients.
  arXiv  Detail & Related papers  (2021-08-12T07:30:42Z)
• An Incentive Mechanism for Federated Learning in Wireless Cellular network: An Auction Approach [75.08185720590748]
  Federated Learning (FL) is a distributed learning framework that can deal with the distributed issue in machine learning. In this paper, we consider a FL system that involves one base station (BS) and multiple mobile users. We formulate the incentive mechanism between the BS and mobile users as an auction game where the BS is an auctioneer and the mobile users are the sellers.
  arXiv  Detail & Related papers  (2020-09-22T01:50:39Z)

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.