中文
相关论文

相关论文: Centroid Approximation for Byzantine-Tolerant Fede…

200 篇论文

Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence…

机器学习 · 计算机科学 2022-05-25 Sadegh Farhadkhani , Rachid Guerraoui , Nirupam Gupta , Rafael Pinot , John Stephan

Given a network in which some pairs of nodes can communicate freely, and some subsets of the nodes could be faulty and colluding to disrupt communication, when can messages reliably be sent from one given node to another? We give a new…

分布式、并行与集群计算 · 计算机科学 2015-03-11 Adam Hesterberg , Andrea Lincoln , Jayson Lynch

Federated learning (FL) is a promising solution to enable many AI applications, where sensitive datasets from distributed clients are needed for collaboratively training a global model. FL allows the clients to participate in the training…

机器学习 · 计算机科学 2022-05-09 Houssem Sifaou , Geoffrey Ye Li

Federated Learning (FL) has gained significant attention for its privacy-preserving capabilities, enabling distributed devices to collaboratively train a global model without sharing raw data. However, its distributed nature forces the…

密码学与安全 · 计算机科学 2025-09-03 Chaoyu Zhang , Heng Jin , Shanghao Shi , Hexuan Yu , Sydney Johns , Y. Thomas Hou , Wenjing Lou

In this paper, we study the challenging task of Byzantine-robust decentralized training on arbitrary communication graphs. Unlike federated learning where workers communicate through a server, workers in the decentralized environment can…

机器学习 · 计算机科学 2023-04-21 Lie He , Sai Praneeth Karimireddy , Martin Jaggi

Federated recommendation systems can provide good performance without collecting users' private data, making them attractive. However, they are susceptible to low-cost poisoning attacks that can degrade their performance. In this paper, we…

机器学习 · 计算机科学 2020-06-16 Chen Chen , Jingfeng Zhang , Anthony K. H. Tung , Mohan Kankanhalli , Gang Chen

This paper proposes a federated learning framework designed to achieve \textit{relative fairness} for clients. Traditional federated learning frameworks typically ensure absolute fairness by guaranteeing minimum performance across all…

机器学习 · 统计学 2024-11-05 Shogo Nakakita , Tatsuya Kaneko , Shinya Takamaeda-Yamazaki , Masaaki Imaizumi

Distributed learning has emerged as a leading paradigm for training large machine learning models. However, in real-world scenarios, participants may be unreliable or malicious, posing a significant challenge to the integrity and accuracy…

机器学习 · 计算机科学 2024-06-10 Grigory Malinovsky , Peter Richtárik , Samuel Horváth , Eduard Gorbunov

The widespread adoption of large-scale machine learning models in recent years highlights the need for distributed computing for efficiency and scalability. This work introduces a novel distributed machine learning paradigm --…

机器学习 · 计算机科学 2024-02-27 Horia Magureanu , Naïri Usher

Many areas of deep learning benefit from using increasingly larger neural networks trained on public data, as is the case for pre-trained models for NLP and computer vision. Training such models requires a lot of computational resources…

机器学习 · 计算机科学 2023-01-03 Eduard Gorbunov , Alexander Borzunov , Michael Diskin , Max Ryabinin

This work presents a new distributed Byzantine tolerant federated learning algorithm, HoldOut SGD, for Stochastic Gradient Descent (SGD) optimization. HoldOut SGD uses the well known machine learning technique of holdout estimation, in a…

分布式、并行与集群计算 · 计算机科学 2020-08-12 Shahar Azulay , Lior Raz , Amir Globerson , Tomer Koren , Yehuda Afek

Decentralized learning has gained great popularity to improve learning efficiency and preserve data privacy. Each computing node makes equal contribution to collaboratively learn a Deep Learning model. The elimination of centralized…

机器学习 · 计算机科学 2021-10-22 Shangwei Guo , Tianwei Zhang , Han Yu , Xiaofei Xie , Lei Ma , Tao Xiang , Yang Liu

In large-scale distributed learning, security issues have become increasingly important. Particularly in a decentralized environment, some computing units may behave abnormally, or even exhibit Byzantine failures -- arbitrary and…

机器学习 · 计算机科学 2021-02-26 Dong Yin , Yudong Chen , Kannan Ramchandran , Peter Bartlett

Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under…

密码学与安全 · 计算机科学 2025-09-11 Charuka Herath , Yogachandran Rahulamathavan , Varuna De Silva , Sangarapillai Lambotharan

Decentralized learning, which facilitates joint model training across geographically scattered agents, has gained significant attention in the field of signal and information processing in recent years. While the optimization errors of…

机器学习 · 计算机科学 2025-06-12 Haoxiang Ye , Tao Sun , Qing Ling

Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effectively remains…

机器学习 · 计算机科学 2023-10-06 Rachid Guerraoui , Nirupam Gupta , Rafael Pinot , Sebastien Rouault , John Stephan

Network traffic prediction plays a crucial role in intelligent network operation. Traditional prediction methods often rely on centralized training, necessitating the transfer of vast amounts of traffic data to a central server. This…

机器学习 · 计算机科学 2025-05-27 Hui Ma , Kai Yang , Yang Jiao

In Federated Learning (FL), the distributed nature and heterogeneity of client data present both opportunities and challenges. While collaboration among clients can significantly enhance the learning process, not all collaborations are…

机器学习 · 计算机科学 2024-07-18 Nazarii Tupitsa , Samuel Horváth , Martin Takáč , Eduard Gorbunov

Federated learning (FL) is an emerging distributed learning paradigm without sharing participating clients' private data. However, existing works show that FL is vulnerable to both Byzantine (security) attacks and data reconstruction…

密码学与安全 · 计算机科学 2024-07-30 Chenfei Nie , Qiang Li , Yuxin Yang , Yuede Ji , Binghui Wang

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify…

机器学习 · 计算机科学 2023-05-02 Jian Xu , Shao-Lun Huang , Linqi Song , Tian Lan