iDML: Incentivized Decentralized Machine Learning

• URL: http://arxiv.org/abs/2304.05354v1
• Date: Mon, 10 Apr 2023 17:28:51 GMT
• Title: iDML: Incentivized Decentralized Machine Learning
• Authors: Haoxiang Yu, Hsiao-Yuan Chen, Sangsu Lee, Sriram Vishwanath, Xi Zheng, Christine Julien
• Abstract summary: We propose a novel blockchain-based incentive mechanism for completely decentralized and opportunistic learning architectures. We leverage a smart contract not only for providing explicit incentives to end devices to participate but also to create a fully decentralized mechanism to inspect and reflect on the behavior of the learning architecture.
• Score: 16.31868012716559
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rising emergence of decentralized and opportunistic approaches to machine learning, end devices are increasingly tasked with training deep learning models on-devices using crowd-sourced data that they collect themselves. These approaches are desirable from a resource consumption perspective and also from a privacy preservation perspective. When the devices benefit directly from the trained models, the incentives are implicit - contributing devices' resources are incentivized by the availability of the higher-accuracy model that results from collaboration. However, explicit incentive mechanisms must be provided when end-user devices are asked to contribute their resources (e.g., computation, communication, and data) to a task performed primarily for the benefit of others, e.g., training a model for a task that a neighbor device needs but the device owner is uninterested in. In this project, we propose a novel blockchain-based incentive mechanism for completely decentralized and opportunistic learning architectures. We leverage a smart contract not only for providing explicit incentives to end devices to participate in decentralized learning but also to create a fully decentralized mechanism to inspect and reflect on the behavior of the learning architecture.

Related papers

• Uncertainty Estimation in Multi-Agent Distributed Learning [0.0]
  KDT NEUROKIT2E project aims to establish a new open-source framework to facilitate AI applications on edge devices. Our research focuses on the mechanisms and methodologies that allow edge network-enabled agents to engage in collaborative learning in distributed environments.
  arXiv  Detail & Related papers  (2023-11-22T12:48:20Z)
• PredictChain: Empowering Collaboration and Data Accessibility for AI in a Decentralized Blockchain-based Marketplace [1.4364491422470593]
  We propose a blockchain-based marketplace called "PredictChain" for predictive machine-learning models. This marketplace enables users to upload datasets for training predictive machine learning models, request model training on previously uploaded datasets, or submit queries to trained models.
  arXiv  Detail & Related papers  (2023-07-27T19:56:18Z)
• IoT Federated Blockchain Learning at the Edge [14.689706366051956]
  We propose a distributed federated learning framework for IoT devices, more specifically for IoMT (Internet of Medical Things) We use blockchain to allow for a decentralized scheme improving privacy and efficiency over a centralized system. The system is designed for three paradigms: 1) Training neural networks on IoT devices to allow for collaborative training of a shared model whilst decoupling the learning from the dataset to ensure privacy.
  arXiv  Detail & Related papers  (2023-04-06T11:32:40Z)
• Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models [103.71308117592963]
  We present an algorithm for training self-destructing models leveraging techniques from meta-learning and adversarial learning. In a small-scale experiment, we show MLAC can largely prevent a BERT-style model from being re-purposed to perform gender identification.
  arXiv  Detail & Related papers  (2022-11-27T21:43:45Z)
• Motivating Learners in Multi-Orchestrator Mobile Edge Learning: A Stackelberg Game Approach [54.28419430315478]
  Mobile Edge Learning enables distributed training of Machine Learning models over heterogeneous edge devices. In MEL, the training performance deteriorates without the availability of sufficient training data or computing resources. We propose an incentive mechanism, where we formulate the orchestrators-learners interactions as a 2-round Stackelberg game.
  arXiv  Detail & Related papers  (2021-09-25T17:27:48Z)
• 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)
• An Incentive-Based Mechanism for Volunteer Computing using Blockchain [13.348848214843345]
  This article introduces a blockchain-enabled resource sharing and service solution through volunteer computing. The proposed solution can achieve high reward distribution, increased number of blockchain formations, reduced delays, and balanced resource usage.
  arXiv  Detail & Related papers  (2020-09-24T18:48:22Z)
• 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)
• Trading Data For Learning: Incentive Mechanism For On-Device Federated Learning [25.368195601622688]
  Federated Learning rests on the notion of training a global model distributedly on various devices. Under this setting, users' devices perform computations on their own data and then share the results with the cloud server to update the global model. The users suffer from privacy leakage of their local data during the federated model training process. We propose an effective incentive mechanism, which selects users that are most likely to provide reliable data and compensates for their costs of privacy leakage.
  arXiv  Detail & Related papers  (2020-09-11T18:37:58Z)
• Incentive Mechanism Design for Resource Sharing in Collaborative Edge Learning [106.51930957941433]
  In 5G and Beyond networks, Artificial Intelligence applications are expected to be increasingly ubiquitous. This necessitates a paradigm shift from the current cloud-centric model training approach to the Edge Computing based collaborative learning scheme known as edge learning.
  arXiv  Detail & Related papers  (2020-05-31T12:45:06Z)
• Resource Management for Blockchain-enabled Federated Learning: A Deep Reinforcement Learning Approach [54.29213445674221]
  Federated Learning (BFL) enables mobile devices to collaboratively train neural network models required by a Machine Learning Model Owner (MLMO) The issue of BFL is that the mobile devices have energy and CPU constraints that may reduce the system lifetime and training efficiency. We propose to use the Deep Reinforcement Learning (DRL) to derive the optimal decisions for theO.
  arXiv  Detail & Related papers  (2020-04-08T16:29:19Z)

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.