paper-with-me

홈 › Papers

FedFNN: Faster Training Convergence Through Update Predictions in Federated Recommender Systems

2023-09-14 · Francesco Fabbri, Xianghang Liu, Jack R. McKenzie, Bartlomiej Twardowski, Tri Kurniawan Wijaya

Federated Learning (FL) has emerged as a key approach for distributed machine learning, enhancing online personalization while ensuring user data privacy. Instead of sending private data to a central server as in traditional approaches, FL decentralizes computations: devices train locally and share updates with a global server. A primary challenge in this setting is achieving fast and accurate model training - vital for recommendation systems where delays can compromise user engagement. This paper introduces FedFNN, an algorithm that accelerates decentralized model training. In FL, only a subset of users are involved in each training epoch. FedFNN employs supervised learning to predict weight updates from unsampled users, using updates from the sampled set. Our evaluations, using real and synthetic data, show: 1. FedFNN achieves training speeds 5x faster than leading methods, maintaining or improving accuracy; 2. the algorithm's performance is consistent regardless of client cluster variations; 3. FedFNN outperforms other methods in scenarios with limited client availability, converging more quickly.

📄 PDF Abstract BibTeX arXiv:2309.08635

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningRecommendation Systems

Similar Papers 제목 키워드 기반

Federated Fuzzy Neural Network with Evolutionary Rule Learning

2022-10-26 · Leijie Zhang, Ye Shi, Yu-Cheng Chang, Chin-Teng Lin

Distributed fuzzy neural networks (DFNNs) have attracted increasing attention recently due to their learning abilities in handling data uncertainties in distributed scenarios. However, it is challenging for DFNNs to hand…

OD-SGD: One-step Delay Stochastic Gradient Descent for Distributed Training

2020-05-14 · Yemao Xu, Dezun Dong, Weixia Xu, Xiangke Liao

The training of modern deep learning neural network calls for large amounts of computation, which is often provided by GPUs or other specific accelerators. To scale out to achieve faster training speed, two update algori…

Distributed Machine Learning through Heterogeneous Edge Systems

2019-11-16 · Hanpeng Hu, Dan Wang, Chuan Wu

Many emerging AI applications request distributed machine learning (ML) among edge systems (e.g., IoT devices and PCs at the edge of the Internet), where data cannot be uploaded to a central venue for model training, due…

BIG-bench Machine Learning

Grams: Gradient Descent with Adaptive Momentum Scaling

2024-12-22 · Yang Cao, Xiaoyu Li, Zhao Song

We introduce $\mathbf{G}$radient Descent with $\mathbf{A}$daptive $\mathbf{M}$omentum $\mathbf{S}$caling ($\mathbf{Grams}$), a novel optimization algorithm that decouples the direction and magnitude of parameter updates …

Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates

2024-02-04 · Zhuanghua Liu, Luo Luo, Bryan Kian Hsiang Low

We consider the finite-sum optimization problem, where each component function is strongly convex and has Lipschitz continuous gradient and Hessian. The recently proposed incremental quasi-Newton method is based on BFGS …