Federated learning (FL) has attracted increasing attention as a promising approach to driving a vast number of end devices with artificial intelligence. However, it is very challenging to guarantee the efficiency of FL considering the unreliable nature of end devices while the cost of device-server communication cannot be neglected. In this paper, we propose SAFA, a semi-asynchronous FL protocol, to address the problems in federated learning such as low round efficiency and poor convergence rate in extreme conditions (e.g., clients dropping offline frequently). We introduce novel designs in the steps of model distribution, client selection and global aggregation to mitigate the impacts of stragglers, crashes and model staleness in order to boost efficiency and improve the quality of the global model. We have conducted extensive experiments with typical machine learning tasks. The results demonstrate that the proposed protocol is effective in terms of shortening federated round duration, reducing local resource wastage, and improving the accuracy of the global model at an acceptable communication cost.

The issue of potential privacy leakage during centralized AIs model training has drawn intensive concern from the public. A Parallel and Distributed Computing (or PDC) scheme, termed Federated Learning (FL), has emerged as a new paradigm to cope with the privacy issue by allowing clients to perform model training locally without uploading their personal sensitive data. In FL, the number of clients could be sufficiently large, but the bandwidth available for model distribution and re-upload is quite limited, making it sensible to only involve part of the volunteers to participate in the training process. The selection policy is critical to an FL process in terms of round efficiency, the final models quality as well as fairness. In this paper, we will model the fairness guaranteed client selection as a Lyapunov optimization problem and then a C2MAB-based method is proposed for estimating the model exchange time between each client and the server, based on which we design a fairness guaranteed algorithm termed RBCS-F for problem-solving. The regret of RBCS-F is strictly bounded by a finite constant, justifying its theoretical feasibility. In addition to the theoretical results, more empirical ones can be derived from our real training experiments on public datasets.

Due to the imbalanced distribution of business data, missing user features, and many other reasons, directly using big data techniques on realistic business data tends to deviate from the business goals. It is difficult to model the insurance business data by classification algorithms, such as logistic regression and support vector machine (SVM). In this paper, we exploit a heuristic bootstrap sampling approach combined with the ensemble learning algorithm on the large-scale insurance business data mining, and propose an ensemble random forest algorithm that uses the parallel computing capability and memory-cache mechanism optimized by Spark. We collected the insurance business data from China Life Insurance Company to analyze the potential customers using the proposed algorithm. We use F-Measure and G-mean to evaluate the performance of the algorithm. Experiment result shows that the ensemble random forest algorithm outperformed SVM and other classification algorithms in both performance and accuracy within the imbalanced data, and it is useful for improving the accuracy of product marketing compared to the traditional artificial approach.

Federated learning (FL), arising as a privacy-preserving machine learning paradigm, has received notable attention from the public. In each round of synchronous FL training, only a fraction of available clients are chosen to participate, and the selection decision might have a significant effect on the training efficiency, as well as the final model performance. In this article, we investigate the client selection problem under a volatile context, in which the local training of heterogeneous clients is likely to fail due to various kinds of reasons and in different levels of frequency. Intuitively, too much training failure might potentially reduce the training efficiency, while too much selection on clients with greater stability might introduce bias, thereby resulting in degradation of the training effectiveness. To tackle this tradeoff, we, in this article, formulate the client selection problem under joint consideration of effective participation and fairness. Furthermore, we propose E3CS, a stochastic client selection scheme as a solution. According to our experimental results over a public data set, the proposed selection scheme is able to achieve up to $2\times $ faster convergence to a fixed model accuracy while maintaining the same level of final model accuracy, compared with the state-of-the-art selection schemes.

With the proliferation of the Internet of Things (IoT) applications, advanced time-series forecasting techniques have become increasingly critical for managing and responding to complex temporal dynamics. However, traditional recurrent neural network (RNN)-based methods have faced challenges in the long-term time-series forecasting (LTSF) domain when dealing with excessively long look-back windows and forecast horizons. Consequently, the dominance in this domain has shifted toward Transformer, multilayer perceptron (MLP), and convolutional neural network (CNN) approaches. The substantial number of recurrent iterations is the fundamental reason behind the limitations of RNNs in LTSF. To address these issues, we propose two novel strategies to reduce the number of iterations in RNNs for LTSF tasks: segment-wise iterations and parallel multistep forecasting (PMF). RNNs that combine these strategies, called SegRNN, significantly reduce the required recurrent iterations for LTSF, resulting in notable improvements in forecast accuracy and inference speed. Extensive experiments demonstrate that SegRNN not only outperforms state-of-the-art Transformer-based models but also reduces runtime and memory usage by more than 78%, making it highly suitable for resource-constrained IoT scenarios. These achievements provide strong evidence that RNNs continue to excel in LTSF tasks and encourage further exploration of this domain with more RNN-based approaches. The code is available at: https://github.com/lss-1138/SegRNN.