اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدSecond-Order Guarantees in Federated Learning
69
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Federated learning is a useful framework for centralized learning from distributed data under practical considerations of heterogeneity, asynchrony, and privacy. Federated architectures are frequently deployed in deep learning settings, which generally give rise to non-convex optimization problems. Nevertheless, most existing analysis are either limited to convex loss functions, or only establish first-order stationarity, despite the fact that saddle-points, which are first-order stationary, are known to pose bottlenecks in deep learning. We draw on recent results on the second-order optimality of stochastic gradient algorithms in centralized and decentralized settings, and establish second-order guarantees for a class of federated learning algorithms.
قيم البحث
اقرأ أيضاً
Federated learning (FL) has emerged as a prominent distributed learning paradigm. FL entails some pressing needs for developing novel parameter estimation approaches with theoretical guarantees of convergence, which are also communication efficient,
differentially private and Byzantine resilient in the heterogeneous data distribution settings. Quantization-based SGD solvers have been widely adopted in FL and the recently proposed SIGNSGD with majority vote shows a promising direction. However, no existing methods enjoy all the aforementioned properties. In this paper, we propose an intuitively-simple yet theoretically-sound method based on SIGNSGD to bridge the gap. We present Stochastic-Sign SGD which utilizes novel stochastic-sign based gradient compressors enabling the aforementioned properties in a unified framework. We also present an error-feedback variant of the proposed Stochastic-Sign SGD which further improves the learning performance in FL. We test the proposed method with extensive experiments using deep neural networks on the MNIST dataset and the CIFAR-10 dataset. The experimental results corroborate the effectiveness of the proposed method.
The Internet of Things (IoT) revolution has shown potential to give rise to many medical applications with access to large volumes of healthcare data collected by IoT devices. However, the increasing demand for healthcare data privacy and security ma
kes each IoT device an isolated island of data. Further, the limited computation and communication capacity of wearable healthcare devices restrict the application of vanilla federated learning. To this end, we propose an advanced federated learning framework to train deep neural networks, where the network is partitioned and allocated to IoT devices and a centralized server. Then most of the training computation is handled by the powerful server. The sparsification of activations and gradients significantly reduces the communication overhead. Empirical study have suggested that the proposed framework guarantees a low accuracy loss, while only requiring 0.2% of the synchronization traffic in vanilla federated learning.
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients. Here we propose an alternative, where each client only federates with oth
er relevant clients to obtain a stronger model per client-specific objectives. To achieve this personalization, rather than computing a single model average with constant weights for the entire federation as in traditional FL, we efficiently calculate optimal weighted model combinations for each client, based on figuring out how much a client can benefit from anothers model. We do not assume knowledge of any underlying data distributions or client similarities, and allow each client to optimize for arbitrary target distributions of interest, enabling greater flexibility for personalization. We evaluate and characterize our method on a variety of federated settings, datasets, and degrees of local data heterogeneity. Our method outperforms existing alternatives, while also enabling new features for personalized FL such as transfer outside of local data distributions.
A new machine learning (ML) technique termed as federated learning (FL) aims to preserve data at the edge devices and to only exchange ML model parameters in the learning process. FL not only reduces the communication needs but also helps to protect
the local privacy. Although FL has these advantages, it can still experience large communication latency when there are massive edge devices connected to the central parameter server (PS) and/or millions of model parameters involved in the learning process. Over-the-air computation (AirComp) is capable of computing while transmitting data by allowing multiple devices to send data simultaneously by using analog modulation. To achieve good performance in FL through AirComp, user scheduling plays a critical role. In this paper, we investigate and compare different user scheduling policies, which are based on various criteria such as wireless channel conditions and the significance of model updates. Receiver beamforming is applied to minimize the mean-square-error (MSE) of the distortion of function aggregation result via AirComp. Simulation results show that scheduling based on the significance of model updates has smaller fluctuations in the training process while scheduling based on channel condition has the advantage on energy efficiency.
In this paper, we focus on facilitating differentially private quantized communication between the clients and server in federated learning (FL). Towards this end, we propose to have the clients send a textit{private quantized} version of only the te
xtit{unit vector} along the change in their local parameters to the server, textit{completely throwing away the magnitude information}. We call this algorithm texttt{DP-NormFedAvg} and show that it has the same order-wise convergence rate as texttt{FedAvg} on smooth quasar-convex functions (an important class of non-convex functions for modeling optimization of deep neural networks), thereby establishing that discarding the magnitude information is not detrimental from an optimization point of view. We also introduce QTDL, a new differentially private quantization mechanism for unit-norm vectors, which we use in texttt{DP-NormFedAvg}. QTDL employs textit{discrete} noise having a Laplacian-like distribution on a textit{finite support} to provide privacy. We show that under a growth-condition assumption on the per-sample client losses, the extra per-coordinate communication cost in each round incurred due to privacy by our method is $mathcal{O}(1)$ with respect to the model dimension, which is an improvement over prior work. Finally, we show the efficacy of our proposed method with experiments on fully-connected neural networks trained on CIFAR-10 and Fashion-MNIST.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
