The Implications of Decentralization in Blockchained Federated Learning: Evaluating the Impact of Model Staleness and Inconsistencies
- URL: http://arxiv.org/abs/2310.07471v2
- Date: Mon, 25 Mar 2024 11:07:13 GMT
- Title: The Implications of Decentralization in Blockchained Federated Learning: Evaluating the Impact of Model Staleness and Inconsistencies
- Authors: Francesc Wilhelmi, Nima Afraz, Elia Guerra, Paolo Dini,
- Abstract summary: We study the practical implications of outsourcing the orchestration of federated learning to a democratic setting such as in a blockchain.
Using simulation, we evaluate the blockchained FL operation by applying two different ML models on the well-known MNIST and CIFAR-10 datasets.
Our results show the high impact of model inconsistencies on the accuracy of the models (up to a 35% decrease in prediction accuracy)
- Score: 2.6391879803618115
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Blockchain promises to enhance distributed machine learning (ML) approaches such as federated learning (FL) by providing further decentralization, security, immutability, and trust, which are key properties for enabling collaborative intelligence in next-generation applications. Nonetheless, the intrinsic decentralized operation of peer-to-peer (P2P) blockchain nodes leads to an uncharted setting for FL, whereby the concepts of FL round and global model become meaningless, as devices' synchronization is lost without the figure of a central orchestrating server. In this paper, we study the practical implications of outsourcing the orchestration of FL to a democratic setting such as in a blockchain. In particular, we focus on the effects that model staleness and inconsistencies, endorsed by blockchains' modus operandi, have on the training procedure held by FL devices asynchronously. Using simulation, we evaluate the blockchained FL operation by applying two different ML models (ranging from low to high complexity) on the well-known MNIST and CIFAR-10 datasets, respectively, and focus on the accuracy and timeliness of the solutions. Our results show the high impact of model inconsistencies on the accuracy of the models (up to a ~35% decrease in prediction accuracy), which underscores the importance of properly designing blockchain systems based on the characteristics of the underlying FL application.
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) - AEDFL: Efficient Asynchronous Decentralized Federated Learning with
Heterogeneous Devices [61.66943750584406]
We propose an Asynchronous Efficient Decentralized FL framework, i.e., AEDFL, in heterogeneous environments.
First, we propose an asynchronous FL system model with an efficient model aggregation method for improving the FL convergence.
Second, we propose a dynamic staleness-aware model update approach to achieve superior accuracy.
Third, we propose an adaptive sparse training method to reduce communication and computation costs without significant accuracy degradation.
arXiv Detail & Related papers (2023-12-18T05:18:17Z) - Secure Decentralized Learning with Blockchain [13.795131629462798]
Federated Learning (FL) is a well-known paradigm of distributed machine learning on mobile and IoT devices.
To avoid the single point of failure problem in FL, decentralized learning (DFL) has been proposed to use peer-to-peer communication for model aggregation.
arXiv Detail & Related papers (2023-10-10T23:45:17Z) - Scheduling and Aggregation Design for Asynchronous Federated Learning
over Wireless Networks [56.91063444859008]
Federated Learning (FL) is a collaborative machine learning framework that combines on-device training and server-based aggregation.
We propose an asynchronous FL design with periodic aggregation to tackle the straggler issue in FL systems.
We show that an age-aware'' aggregation weighting design can significantly improve the learning performance in an asynchronous FL setting.
arXiv Detail & Related papers (2022-12-14T17:33:01Z) - Blockchain-based Monitoring for Poison Attack Detection in Decentralized
Federated Learning [2.322461721824713]
Federated Learning (FL) is a machine learning technique that addresses the privacy challenges in terms of access rights of local datasets.
In decentralized FL, the chief is eliminated from the learning process as workers collaborate between each other to train the global model.
We propose a technique which consists in decoupling the monitoring phase from the detection phase in defenses against poisoning attacks.
arXiv Detail & Related papers (2022-09-30T19:07:29Z) - On the Decentralization of Blockchain-enabled Asynchronous Federated
Learning [3.3701306798873305]
Federated learning (FL) is expected to enable true real-time applications in production environments.
The empowerment of FL through blockchain (also referred to as FLchain) has some implications in terms of ledger inconsistencies and age of information (AoI)
In this paper, we shed light on the implications of the FLchain setting and study the effect that both the AoI and ledger inconsistencies have on the FL performance.
arXiv Detail & Related papers (2022-05-20T14:20:47Z) - Towards On-Device Federated Learning: A Direct Acyclic Graph-based
Blockchain Approach [2.9202274421296943]
This paper introduces a framework for empowering Federated Learning using Direct Acyclic Graph (DAG)-based blockchain systematically (DAG-FL)
Two algorithms DAG-FL Controlling and DAG-FL Updating are designed running on different nodes to elaborate the operation of DAG-FL consensus mechanism.
arXiv Detail & Related papers (2021-04-27T10:29:38Z) - Blockchain Assisted Decentralized Federated Learning (BLADE-FL):
Performance Analysis and Resource Allocation [119.19061102064497]
We propose a decentralized FL framework by integrating blockchain into FL, namely, blockchain assisted decentralized federated learning (BLADE-FL)
In a round of the proposed BLADE-FL, each client broadcasts its trained model to other clients, competes to generate a block based on the received models, and then aggregates the models from the generated block before its local training of the next round.
We explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
arXiv Detail & Related papers (2021-01-18T07:19:08Z) - Robust Blockchained Federated Learning with Model Validation and
Proof-of-Stake Inspired Consensus [43.12040317316018]
Federated learning (FL) is a promising distributed learning solution that only exchanges model parameters without revealing raw data.
We propose a blockchain-based decentralized FL framework, termed VBFL, by exploiting two mechanisms in a blockchained architecture.
With 15% of malicious devices, VBFL achieves 87% accuracy, which is 7.4x higher than Vanilla FL.
arXiv Detail & Related papers (2021-01-09T06:30:38Z) - Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with
Lazy Clients [124.48732110742623]
We propose a novel framework by integrating blockchain into Federated Learning (FL)
BLADE-FL has a good performance in terms of privacy preservation, tamper resistance, and effective cooperation of learning.
It gives rise to a new problem of training deficiency, caused by lazy clients who plagiarize others' trained models and add artificial noises to conceal their cheating behaviors.
arXiv Detail & Related papers (2020-12-02T12:18:27Z) - 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.