Non-independent and identically distributed (non-IID) data distribution among clients is considered as the key factor that degrades the performance of federated learning (FL). Several approaches to handle non-IID data, such as personalized FL and federated multitask learning (FMTL), are of great interest to research communities. In this work, first, we formulate the FMTL problem using Laplacian regularization to explicitly leverage the relationships among the models of clients for multitask learning. Then, we introduce a new view of the FMTL problem, which, for the first time, shows that the formulated FMTL problem can be used for conventional FL and personalized FL. We also propose two algorithms FedU and decentrali- zed FedU ( dFedU ) to solve the formulated FMTL problem in communication-centralized and decentralized schemes, respectively. Theoretically, we prove that the convergence rates of both algorithms achieve linear speedup for strongly convex and sublinear speedup of order 1/2 for nonconvex objectives. Experimentally, we show that our algorithms outperform the conventional algorithm FedAvg, FedProx, SCAFFOLD, and AFL in FL settings, MOCHA in FMTL settings, as well as pFedMe and Per-FedAvg in personalized FL settings.

There is growing interest in applying distributed machine learning to edge computing, formingfederated edge learning. Federated edge learning faces non-i.i.d. and heterogeneous data, and the communication between edge workers, possibly through distant locations and with unstable wireless networks, is more costly than their local computational overhead. In this work, we propose${{\sf DONE}}$, a distributed approximate Newton-type algorithm with fast convergence rate for communication-efficient federated edge learning. First, with strongly convex and smooth loss functions,${{\sf DONE}}$approximates the Newton direction in a distributed manner using the classical Richardson iteration on each edge worker. Second, we prove that${{\sf DONE}}$has linear-quadratic convergence and analyze its communication complexities. Finally, the experimental results with non-i.i.d. and heterogeneous data show that${{\sf DONE}}$attains a comparable performance to Newton's method. Notably,${{\sf DONE}}$requires fewer communication iterations compared to distributed gradient descent and outperforms DANE, FEDL, and GIANT, state-of-the-art approaches, in the case of non-quadratic loss functions.

There is an increasing interest in a fast-growing machine learning technique called Federated Learning (FL), in which the model training is distributed over mobile user equipment (UEs), exploiting UEs' local computation and training data. Despite its advantages such as preserving data privacy, FL still has challenges of heterogeneity across UEs' data and physical resources. To address these challenges, we first propose FEDL, a FL algorithm which can handle heterogeneous UE data without further assumptions except strongly convex and smooth loss functions. We provide a convergence rate characterizing the trade-off between local computation rounds of each UE to update its local model and global communication rounds to update the FL global model. We then employ FEDL in wireless networks as a resource allocation optimization problem that captures the trade-off between FEDL convergence wall clock time and energy consumption of UEs with heterogeneous computing and power resources. Even though the wireless resource allocation problem of FEDL is non-convex, we exploit this problem's structure to decompose it into three sub-problems and analyze their closed-form solutions as well as insights into problem design. Finally, we empirically evaluate the convergence of FEDL with PyTorch experiments, and provide extensive numerical results for the wireless resource allocation sub-problems. Experimental results show that FEDL outperforms the vanilla FedAvg algorithm in terms of convergence rate and test accuracy in various settings.

Federated Learning (FL) is a fast-developing distributed machine learning technique involving the participation of a massive number of user devices. While FL has benefits of data privacy and the abundance of user-generated data, its challenges of heterogeneity across users’ data and devices complicate algorithm design and convergence analysis. To tackle these challenges, we propose an algorithm that exploits proximal stochastic variance reduced gradient methods for non-convex FL. The proposed algorithm consists of two nested loops, which allow user devices to update their local models approximately up to an accuracy threshold (inner loop) before sending these local models to the server for global model update (outer loop). We characterize the convergence conditions for both local and global model updates and extract various insights from these conditions via the algorithm’s parameter control. We also propose how to optimize these parameters such that the training time of FL is minimized. Experimental results not only validate the theoretical convergence but also show that the proposed algorithm outperforms existing Stochastic Gradient Descent-based methods in terms of convergence speed in FL setting.

Federated learning (FL) is a decentralized and privacy-preserving machine learning technique in which a group of clients collaborate with a server to learn a global model without sharing clients' data. One challenge associated with FL is statistical diversity among clients, which restricts the global model from delivering good performance on each client's task. To address this, we propose an algorithm for personalized FL (pFedMe) using Moreau envelopes as clients' regularized loss functions, which help decouple personalized model optimization from the global model learning in a bi-level problem stylized for personalized FL. Theoretically, we show that pFedMe convergence rate is state-of-the-art: achieving quadratic speedup for strongly convex and sublinear speedup of order 2/3 for smooth nonconvex objectives. Experimentally, we verify that pFedMe excels at empirical performance compared with the vanilla FedAvg and Per-FedAvg, a meta-learning based personalized FL algorithm.