Federated learning has emerged as a promising distributed machine learning paradigm to preserve data privacy. One of the fundamental challenges of federated learning is that data samples across clients are usually not independent and identically distributed (non-IID), leading to slow convergence and severe performance drop of the aggregated global model. To facilitate model aggregation on non-IID data, it is desirable to infer the unknown global distributions without violating privacy protection policy. In this paper, we propose a novel data-agnostic distribution fusion based model aggregation method called FedFusion to optimize federated learning with non-IID local datasets, based on which the heterogeneous clients' data distributions can be represented by a global distribution of several virtual fusion components with different parameters and weights. We develop a Variational AutoEncoder (VAE) method to learn the optimal parameters of the distribution fusion components based on limited statistical information extracted from the local models, and apply the derived distribution fusion model to optimize federated model aggregation with non-IID data. Extensive experiments based on various federated learning scenarios with real-world datasets show that FedFusion achieves significant performance improvement compared to the state-of-the-art.

Multivariate time series (MTS) clustering is an important technique for discovering co-evolving patterns and interpreting group characteristics in many areas including economics, bioinformatics, data science, etc. Although time series clustering has been widely studied in the past decades, no enough attention has been paid to capture time-varying correlation patterns in MTS. In this article, we propose a novel clustering approach for MTS data based on time-varying features. We introduce a time-varying Gaussian Markov Random Fields (T-GMRF) model to describe the correlation structure between MTS variables, and formulate the time-varying feature extraction problem as a convex optimization problem, which can be solved by a T-GMRF learning algorithm based on random block coordinate descent. We further apply a principal component analysis (PCA) based method on GMRF sequences to obtain low-dimensional feature vectors, and adopt a multi-density based clustering approach to form the cluster assignments. We conduct extensive experiments to compare the proposed T-GMRF method with 11 clustering algorithms based on 33 open MTS datasets, which show that T-GMRF significantly outperforms the state-of-the-arts with performance improvement up to 16%-64.5% on a variety of clustering performance metrics. The source codes of T-GMRF are publicly available at GitHub.

Federated learning (FL) has been proposed as a novel paradigm to enable distributed learning on the edge with privacy protection. However, existing federated learning approaches mainly focus on training deep classification and clustering models, and no enough attention has been paid to solve the federated reinforcement learning task on the edge, a challenging task where multiple learning agents observe local state and take local actions to train a global learning model without revealing their local dataset. In this paper, we propose a generalised federated reinforcement learning framework called FedMC that integrates reinforcement learning models trained by multiple edge devices into a general model based on a meta-learning approach. In the proposed framework, each participant adopts a meta-value network (MVN) and task-actor encoder network (TAEN) locally to perform meta-learning training based on local task samples, and periodically uploads the weights of local MVN and TAEN to the server, which aggregate them to a global model with rapid adaptability and cross-task applicability. Extensive experiments based on a number of reinforcement learning tasks show that FedMC outperforms various federated learning baseline algorithms, and it is competitive with the methods that centrally train reinforcement learning task with global dataset.