paper-with-me

홈 › Papers

CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems

2021-05-29 · Jiahao Xie, Chao Zhang, Zebang Shen, Weijie Liu, Hui Qian

Minimax problems arise in a wide range of important applications including robust adversarial learning and Generative Adversarial Network (GAN) training. Recently, algorithms for minimax problems in the Federated Learning (FL) paradigm have received considerable interest. Existing federated algorithms for general minimax problems require the full aggregation (i.e., aggregation of local model information from all clients) in each training round. Thus, they are inapplicable to an important setting of FL known as the cross-device setting, which involves numerous unreliable mobile/IoT devices. In this paper, we develop the first practical algorithm named CDMA for general minimax problems in the cross-device FL setting. CDMA is based on a Start-Immediately-With-Enough-Responses mechanism, in which the server first signals a subset of clients to perform local computation and then starts to aggregate the local results reported by clients once it receives responses from enough clients in each round. With this mechanism, CDMA is resilient to the low client availability. In addition, CDMA is incorporated with a lightweight global correction in the local update steps of clients, which mitigates the impact of slow network connections. We establish theoretical guarantees of CDMA under different choices of hyperparameters and conduct experiments on AUC maximization, robust adversarial network training, and GAN training tasks. Theoretical and experimental results demonstrate the efficiency of CDMA.

📄 PDF Abstract BibTeX arXiv:2105.14216

Code (1)

xjiajiahao/federated-minimax 공식 구현 pytorch

Tasks

Federated LearningGenerative Adversarial Network

Similar Papers 제목 키워드 기반

CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning

2024-03-15 · CVPR 2024 1 · Hyuck Lee, Heeyoung Kim

Pseudo-label-based semi-supervised learning (SSL) algorithms trained on a class-imbalanced set face two cascading challenges: 1) Classifiers tend to be biased towards majority classes, and 2) Biased pseudo-labels are use…

Pseudo Label

Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models

2023-10-11 · Renyang Liu, Wei Zhou, Tianwei Zhang, Kangjie Chen 외

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large n…

Adversarial AttackDenoising

A Novel Detection Algorithm Efficient for Turbo coded CDMA Signals in Detect and Forward Cooperative Channels

2018-03-12

In this paper, a new detection algorithm is proposed for turbo coded Code Division Multiple Access (CDMA) signals in detect and forward cooperative channels. Use of user cooperation makes much improvement in the performa…

Diversity

CDMA/OTFS Sensing Outperforms Pure OTFS at the Same Communication Throughput

2025-01-20 · Hugo Hawkins, Chao Xu, Lie-Liang Yang, Lajos Hanzo

There is a dearth of publications on the subject of spreading-aided Orthogonal Time Frequency Space (OTFS) solutions, especially for Integrated Sensing and Communication (ISAC), even though Code Division Multiple Access …

Integrated sensing and communicationISACparameter estimation

Federated Select: A Primitive for Communication- and Memory-Efficient Federated Learning

2022-08-19 · Zachary Charles, Kallista Bonawitz, Stanislav Chiknavaryan, Brendan Mcmahan 외

Federated learning (FL) is a framework for machine learning across heterogeneous client devices in a privacy-preserving fashion. To date, most FL algorithms learn a "global" server model across multiple rounds. At each r…

Federated LearningPrivacy Preserving