Proof-of-Collaborative-Learning: A Multi-winner Federated Learning Consensus Algorithm
- URL: http://arxiv.org/abs/2407.13018v2
- Date: Wed, 24 Jul 2024 17:04:35 GMT
- Title: Proof-of-Collaborative-Learning: A Multi-winner Federated Learning Consensus Algorithm
- Authors: Amirreza Sokhankhosh, Sara Rouhani,
- Abstract summary: We propose Proof-of-Collaborative-Learning (PoCL), a multi-winner federated learning validated consensus mechanism.
PoCL redirects the power of blockchains to train federated learning models.
We present a novel evaluation mechanism to ensure the efficiency of the locally trained models of miners.
- Score: 2.5203968759841158
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Regardless of their variations, blockchains require a consensus mechanism to validate transactions, supervise added blocks, maintain network security, synchronize the network state, and distribute incentives. Proof-of-Work (PoW), one of the most influential implementations of consensus mechanisms, consumes an extraordinary amount of energy for a task that lacks direct productive output. In this paper, we propose Proof-of-Collaborative-Learning (PoCL), a multi-winner federated learning validated consensus mechanism that redirects the computation power of blockchains to train federated learning models. In addition, we present a novel evaluation mechanism to ensure the efficiency of the locally trained models of miners. We evaluated the security of our evaluation mechanism by introducing and conducting probable attacks. Moreover, we present a novel reward distribution mechanism to incentivize winning miners fairly, and demonstrate that our reward system is fair both within and across all rounds.
Related papers
- Enhancing Trust and Privacy in Distributed Networks: A Comprehensive Survey on Blockchain-based Federated Learning [51.13534069758711]
Decentralized approaches like blockchain offer a compelling solution by implementing a consensus mechanism among multiple entities.
Federated Learning (FL) enables participants to collaboratively train models while safeguarding data privacy.
This paper investigates the synergy between blockchain's security features and FL's privacy-preserving model training capabilities.
arXiv Detail & Related papers (2024-03-28T07:08:26Z) - Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit [14.822625665220068]
We study a robust multi-agent multi-armed bandit problem where multiple clients or participants are distributed on a fully decentralized blockchain.
We are the first to incorporate advanced techniques from blockchains, as well as novel mechanisms, into the system to design optimal strategies for honest participants.
This is consistent with the multi-agent multi-armed bandit problem without malicious participants and the robust multi-agent multi-armed bandit problem with purely Byzantine attacks.
arXiv Detail & Related papers (2024-02-06T21:33:34Z) - Generative AI-enabled Blockchain Networks: Fundamentals, Applications,
and Case Study [73.87110604150315]
Generative Artificial Intelligence (GAI) has emerged as a promising solution to address challenges of blockchain technology.
In this paper, we first introduce GAI techniques, outline their applications, and discuss existing solutions for integrating GAI into blockchains.
arXiv Detail & Related papers (2024-01-28T10:46:17Z) - Enhancing Scalability and Reliability in Semi-Decentralized Federated
Learning With Blockchain: Trust Penalization and Asynchronous Functionality [0.0]
The paper focuses on enhancing the trustworthiness of participating nodes through a trust penalization mechanism.
The proposed system aims to create a fair, secure and transparent environment for collaborative machine learning without compromising data privacy.
arXiv Detail & Related papers (2023-10-30T06:05:50Z) - Securing Blockchain Systems: A Novel Collaborative Learning Framework to Detect Attacks in Transactions and Smart Contracts [26.85360925398753]
This paper presents a novel collaborative learning framework designed to detect attacks in blockchain transactions and smart contracts.
Our framework exhibits the capability to classify various types of blockchain attacks, including intricate attacks at the machine code level.
Our framework achieves a detection accuracy of approximately 94% through extensive simulations and real-time experiments with a throughput of over 2,150 transactions per second.
arXiv Detail & Related papers (2023-08-30T07:17:20Z) - Defending Against Poisoning Attacks in Federated Learning with
Blockchain [12.840821573271999]
We propose a secure and reliable federated learning system based on blockchain and distributed ledger technology.
Our system incorporates a peer-to-peer voting mechanism and a reward-and-slash mechanism, which are powered by on-chain smart contracts, to detect and deter malicious behaviors.
arXiv Detail & Related papers (2023-07-02T11:23:33Z) - Revisiting QMIX: Discriminative Credit Assignment by Gradient Entropy
Regularization [126.87359177547455]
In cooperative multi-agent systems, agents jointly take actions and receive a team reward instead of individual rewards.
In the absence of individual reward signals, credit assignment mechanisms are usually introduced to discriminate the contributions of different agents.
We propose a new perspective on credit assignment measurement and empirically show that QMIX suffers limited discriminability on the assignment of credits to agents.
arXiv Detail & Related papers (2022-02-09T12:37:55Z) - Finite-Time Consensus Learning for Decentralized Optimization with
Nonlinear Gossiping [77.53019031244908]
We present a novel decentralized learning framework based on nonlinear gossiping (NGO), that enjoys an appealing finite-time consensus property to achieve better synchronization.
Our analysis on how communication delay and randomized chats affect learning further enables the derivation of practical variants.
arXiv Detail & Related papers (2021-11-04T15:36:25Z) - Proof of Learning (PoLe): Empowering Machine Learning with Consensus
Building on Blockchains [7.854034211489588]
We propose a new consensus mechanism, Proof of Learning (PoLe), which directs the spent for consensus toward optimization of neural networks (NN)
In our mechanism, the training/testing data are released to the entire blockchain network (BCN) and the consensus nodes train NN models on the data.
We show that PoLe can achieve a more stable block generation rate, which leads to more efficient transaction processing.
arXiv Detail & Related papers (2020-07-29T22:53:43Z) - Monotonic Value Function Factorisation for Deep Multi-Agent
Reinforcement Learning [55.20040781688844]
QMIX is a novel value-based method that can train decentralised policies in a centralised end-to-end fashion.
We propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning.
arXiv Detail & Related papers (2020-03-19T16:51:51Z) - Byzantine-resilient Decentralized Stochastic Gradient Descent [85.15773446094576]
We present an in-depth study towards the Byzantine resilience of decentralized learning systems.
We propose UBAR, a novel algorithm to enhance decentralized learning with Byzantine Fault Tolerance.
arXiv Detail & Related papers (2020-02-20T05:11:04Z)
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.