Efficient data transfer across scientific computing facilities is critical for enabling timely scientific discoveries. In this work, we explore the options of anticipating extremely slow data transfers to enable preventive actions. However, the dynamic nature of the large distributed scientific workflows driving these data transfers presents significant challenges for predicting network throughput. This study introduces a Conditional Recurrent Neural Network (CondRNN) model, specifically utilizing Conditional Long Short-Term Memory (CondLSTM), to integrate both static and dynamic features for enhanced throughput prediction. By leveraging historical transfers as proxy features, more than 60% of predictions achieved an absolute percentage error (APE) of less than 20%, and slow transfers were detected with a precision of 91.7% and recall of 100%, outperforming traditional RNN models. Implementing CondLSTM in scientific computing environments can optimize network resource utilization, ensuring efficient data transmission, thereby supporting the continuous progression of scientific research.

Foundation models (FMs) have achieved state-of-the-art performance across various domains, benefiting from their vast number of parameters and the extensive amount of publicly available training data. However, real-world deployments reveal challenges such as system heterogeneity, where not all devices can handle the complexity of FMs, and emerging privacy concerns that limit the availability of public data. To address these challenges, we propose HeLoRA, a novel approach combining low-rank adaptation (LoRA) with federated learning to enable heterogeneous federated fine-tuning. HeLoRA allows clients to fine-tune models with different complexities by adjusting the rank values of LoRA matrices, tailoring the process to each device’s capabilities. To tackle the challenge of aggregating models with different structures, HeLoRA introduces two variants, i.e., HeLoRA-Pad and HeLoRA-KD. HeLoRA-Pad employs context-based padding to standardize the LoRA matrices, aligning them with the global model through a rank-based adaptive aggregation strategy. In contrast, HeLoRA-KD leverages the idea of deep mutual learning for aggregation, allowing heterogeneous models to retain their original structures. Extensive experiments with various datasets and ablation studies demonstrate that HeLoRA outperforms existing baselines, promising to enhance the practical deployment of FMs in diverse real-world environments.

As privacy concerns continue to grow, federated learning (FL) has gained significant attention as a promising privacy-preserving technology, leading to considerable advancements in recent years. Unlike traditional machine learning, which requires central data collection, FL keeps data localized on user devices. However, conventional FL assumes that all clients operate with identical model structures initialized by the server. In real-world applications, system heterogeneity is common, with clients possessing varying computational capabilities. This disparity can hinder training for resource-limited clients and result in inefficient resource use for those with greater processing power. To address this challenge, model-heterogeneous FL has been introduced, enabling clients to train models of varying complexity based on their hardware resources. This paper reviews state-of-the-art approaches in model-heterogeneous FL, analyzing their strengths and weaknesses, while identifying open challenges and future research directions. To the best of our knowledge, this is the first survey to specifically focus on model-heterogeneous FL.

Privacy protection in recommendation systems is gaining increasing attention, for which federated learning has emerged as a promising solution. Current federated recommendation systems grapple with high communication overhead due to sharing dense global embeddings, and also poorly reflect user preferences due to data heterogeneity. To overcome these challenges, we propose a two-stage Federated Low-rank Coordinated Adaptation (FedLoCA) framework to decouple global and client-specific knowledge into low-rank embeddings, which significantly reduces communication overhead while enhancing the system’s ability to capture individual user preferences amidst data heterogeneity. Further, to tackle gradient estimation inaccuracies stemming from data sparsity in federated recommendation systems, we introduce an adversarial gradient projected descent approach in low-rank spaces, which significantly boosts model performance while maintaining robustness. Remarkably, FedLoCA also alleviates performance loss even under the stringent constraints of differential privacy. Extensive experiments on various real-world datasets demonstrate that FedLoCA significantly outperforms existing methods in both recommendation accuracy and communication efficiency.

The emergence of distributed machine learning has greatly improved the speed of machine learning model training, however, distributed machine learning is prone to be damaged by Byzantine attacks in practical applications leading to model training failure. In this paper, we investigate the security of distributed machine learning with parameter server architecture and propose a distributed machine learning strategy that can resist malicious attacks. And based on this strategy, a distributed machine learning framework is built using lightweight techniques. The strategy is designed as follows: for the case where the training node suffers from Byzantine attack, the Byzantine fault-tolerant stochastic gradient descent algorithm is used to carry out local gradient aggregation; for the case where the central node of distributed machine learning suffers from malicious attack, the consensus node is selected by using the consensus mechanism of the union chain, and the average gradient of the consensus node is used instead of the global gradient to participate in the training of the global model. The experimental environment is constructed through containerization technology to simulate the distributed machine learning network with high fidelity and low resource consumption. The experimental results show that the anti-Byzantine attack strategy proposed in this paper can effectively defend against Byzantine attacks. Under the same malicious attack scenario, its model accuracy is improved by about 20% compared to the distributed machine learning framework with traditional parameter server architecture.

The Internet of Things (IoT) has revolutionized the connectivity of diverse sensing devices, generating an enormous volume of data. However, applying machine learning algorithms to sensing devices presents substantial challenges due to resource constraints and privacy concerns. Federated learning (FL) emerges as a promising solution allowing for training models in a distributed manner while preserving data privacy on client devices. We contribute SAFI , a semi-asynchronous FL approach based on clustering to achieve a novel in-cluster synchronous and out-cluster asynchronous FL training mode. Specifically, we propose a three-tier architecture to enable IoT data processing on edge devices and design a clustering selection module to effectively group heterogeneous edge devices based on their processing capacities. The performance of SAFI has been extensively evaluated through experiments conducted on a real-world testbed. As the heterogeneity of edge devices increases, SAFI surpasses the baselines in terms of the convergence time, achieving a speedup of approximately × 3 when the heterogeneity ratio is 7:1. Moreover, SAFI demonstrates favorable performance in non-independent and identically distributed settings and requires lower communication cost compared to FedAsync. Notably, SAFI is the first Java-implemented FL approach and holds significant promise to serve as an efficient FL algorithm in IoT environments.

Screen lock is a critical security feature for smartphones to prevent unauthorized access. Although various screen unlocking technologies, including fingerprint and facial recognition, have been widely adopted, they still have some limitations. For example, fingerprints can be stolen by special material stickers and facial recognition systems can be cheated by 3D-printed head models. In this paper, we propose EmgAuth, a novel electromyography(EMG)-based smartphone unlocking system based on the Siamese network. EmgAuth enables users to unlock their smartphones by leveraging the EMG data of the smartphone users collected from Myo armbands. When training the Siamese network, we design a special data augmentation technique to make the system resilient to the rotation of the armband, which makes EmgAuth free of calibration. We conduct extensive experiments including 53 participants and the evaluation results verify that EmgAuth can effectively authenticate users with an average true acceptance rate of 91.81% while keeping the average false acceptance rate of 7.43%. In addition, we also demonstrate that EmgAuth can work well for smartphones with different screen sizes and for different scenarios. EmgAuth shows great promise to serve as a good supplement for existing screen unlocking systems to improve the safety of smartphones.

Screen lock is a critical security feature for smart-phones to prevent unauthorized access. Although various screen unlocking technologies including fingerprint and facial recognition have been widely adopted, they still have some limitations. For example, fingerprints can be stolen by special material stickers and facial recognition systems can be cheated by 3D-printed head models. In this paper, we propose EmgAuth, a novel electromyography(EMG)-based smartphone unlocking system based on the Siamese network. EmgAuth leverages the Myo armband to collect the EMG data of smartphone users and enables users to unlock their smartphones when picking up and watching their smartphones. In particular, when training the Siamese network, we design a special data augmentation technique to make the system resilient to the rotation of the armband. We conduct experiments including 40 participants and the evaluation results show that EmgAuth can effectively authenticate users with an average true acceptance rate of 91.81% while keeping the average false acceptance rate of 7.43%. In addition, we also demonstrate that EmgAuth can work well for smartphones with different sizes and at different locations, and is applicable for users with different postures. EmgAuth bears great promise to serve as a good supplement for existing screen unlocking systems to improve the safety of smartphones.

Among various tools invented to help improve people's oral health, water flossers can achieve better performance than traditional and electronic toothbrushes, and are less harmful than dental floss, especially for those with orthodontic teeth or tooth implant surgeries. However, the water flossers available in the market serve no monitoring or recording functions that can help consumers clean their teeth in a more efficient way. To capture users' motions, this study develops a novel smart water flosser, installing an Inertial Measurement Unit (IMU) sensor on the handle of the flosser. We determine the motion cycle using signal processing techniques and extract a set of statistical characteristics from the data set. We then train and compare different machine learning models as classifiers to recognize the motions of the handle. We find that the Random Forest model achieves the best detection accuracy at 97% and 85% of the whole feature set and optimized set, respectively. Finally we implement an Android App that connects the smart water flosser with a Bluetooth module to show the washing area in real-time and record relevant information for further guidance.