More Like this

1. Fedband: Adaptive Federated Learning with Bandwidth Constraints

   Alanazi, T; Fahim, A; Ibnath, M; Guler, B; Roy-Chowdhury, A; Swami, A; Papalexakis, E; Krishnamurthy, S (August 2025, IEEE International Conference on Computers Communications and Networks (ICCCN))

   Li, R; Chowdhury, K (Ed.)

   Federated Learning (FL) enables model training across decentralized clients while preserving data privacy. However, bandwidth constraints limit the volume of information exchanged, making communication efficiency a critical challenge. In addition, non- IID data distributions require fairness-aware mechanisms to prevent performance degradation for certain clients. Existing sparsification techniques often apply fixed compression ratios uniformly, ignoring variations in client importance and bandwidth. We propose FedBand, a dynamic bandwidth allocation framework that prioritizes clients based on their contribution to the global model. Unlike conventional approaches, FedBand does not enforce uniform client participation in every communication round. Instead, it allocates more bandwidth to clients whose local updates deviate significantly from the global model, enabling them to transmit a greater number of parameters. Clients with less impactful updates contribute proportionally less or may defer transmission, reducing unnecessary overhead while maintaining generalizability. By optimizing the trade-off between communication efficiency and learning performance, FedBand substantially reduces transmission costs while preserving model accuracy. Experiments on non-IID CIFAR-10 and UTMobileNet2021 datasets, demonstrate that FedBand achieves up to 99.81% bandwidth savings per round while maintaining accuracies close to that of an unsparsified model (80% on CIFAR- 10, 95% on UTMobileNet), despite transmitting less than 1% of the model parameters in each round. Moreover, FedBand accelerates convergence by 37.4%, further improving learning efficiency under bandwidth constraints. Mininet emulations further show a 42.6% reduction in communication costs and a 65.57% acceleration in convergence compared to baseline methods, validating its real-world efficiency. These results demonstrate that adaptive bandwidth allocation can significantly enhance the scalability and communication efficiency of federated learning, making it more viable for real- world, bandwidth-constrained networking environments. 

   more » « less
2. Hardware-Sensitive Fairness in Heterogeneous Federated Learning

   https://doi.org/10.1145/3703627  

   Talukder, Zahidur; Lu, Bingqian; Ren, Shaolei; Islam, Mohammad_Atiqul (March 2025, ACM Transactions on Modeling and Performance Evaluation of Computing Systems)

   Federated learning (FL) is a promising technique for decentralized privacy-preserving Machine Learning (ML) with a diverse pool of participating devices with varying device capabilities. However, existing approaches to handle such heterogeneous environments do not consider “fairness” in model aggregation, resulting in significant performance variation among devices. Meanwhile, prior works on FL fairness remain hardware-oblivious and cannot be applied directly without severe performance penalties. To address this issue, we propose a novel hardware-sensitive FL method called\(\mathsf {FairHetero}\)that promotes fairness among heterogeneous federated clients. Our approach offers tunable fairness within a group of devices with the same ML architecture as well as across different groups with heterogeneous models. Our evaluation underMNIST,FEMNIST,CIFAR10, andSHAKESPEAREdatasets demonstrates that\(\mathsf {FairHetero}\)can reduce variance among participating clients’ test loss compared to the existing state-of-the-art techniques, resulting in increased overall performance. 

   more » « less
3. Evaluation of Thermal Stress on Heterogeneous IoT-Based Federated Learning

   https://doi.org/10.3390/electronics13163140  

   Gu, Yi; Zhao, Liang; Liu, Tianze; Wu, Shaoen (August 2024, Electronics)

   Federated learning is a novel paradigm allowing the training of a global machine-learning model on distributed devices. It shares model parameters instead of private raw data during the entire model training process. While federated learning enables machine learning processes to take place collaboratively on Internet of Things (IoT) devices, compared to data centers, IoT devices with limited resource budgets typically have less security protection and are more vulnerable to potential thermal stress. Current research on the evaluation of federated learning is mainly based on the simulation of multi-clients/processes on a single machine/device. However, there is a gap in understanding the performance of federated learning under thermal stress in real-world distributed low-power heterogeneous IoT devices. Our previous work was among the first to evaluate the performance of federated learning under thermal stress on real-world IoT-based distributed systems. In this paper, we extended our work to a larger scale of heterogeneous real-world IoT-based distributed systems to further evaluate the performance of federated learning under thermal stress. To the best of our knowledge, the presented work is among the first to evaluate the performance of federated learning under thermal stress on real-world heterogeneous IoT-based systems. We conducted comprehensive experiments using the MNIST dataset and various performance metrics, including training time, CPU and GPU utilization rate, temperature, and power consumption. We varied the proportion of clients under thermal stress in each group of experiments and systematically quantified the effectiveness and real-world impact of thermal stress on the low-end heterogeneous IoT-based federated learning system. We added 67% more training epochs and 50% more clients compared with our previous work. The experimental results demonstrate that thermal stress is still effective on IoT-based federated learning systems as the entire global model and device performance degrade when even a small ratio of IoT devices are being impacted. Experimental results have also shown that the more influenced client under thermal stress within the federated learning system (FLS) tends to have a more major impact on the performance of FLS under thermal stress. 

   more » « less
4. FedAST: Federated Asynchronous Simultaneous Training

   Askin, Baris; Sharma, Pranay; Joe-Wong, Carlee; Joshi, Gauri (July 2024, Uncertainty in artificial intelligence)

   Federated Learning (FL) enables edge devices or clients to collaboratively train machine learning (ML) models without sharing their private data. Much of the existing work in FL focuses on efficiently learning a model for a single task. In this paper, we study simultaneous training of multiple FL models using a common set of clients. The few existing simultaneous training methods employ synchronous aggregation of client updates, which can cause significant delays because large models and/or slow clients can bottleneck the aggregation. On the other hand, a naive asynchronous aggregation is adversely affected by stale client updates. We propose FedAST, a buffered asynchronous federated simultaneous training algorithm that overcomes bottlenecks from slow models and adaptively allocates client resources across heterogeneous tasks. We provide theoretical convergence guarantees of FedAST for smooth non-convex objective functions. Extensive experiments over multiple real-world datasets demonstrate that our proposed method outperforms existing simultaneous FL approaches, achieving up to 46.0% reduction in time to train multiple tasks to completion. 

   more » « less
5. FedDefender: Backdoor Attack Defense in Federated Learning

   https://doi.org/10.1145/3617574.3617858  

   Gill, Waris; Anwar, Ali; Gulzar, Muhammad Ali (December 2023, ACM)

   Federated Learning (FL) is a privacy-preserving distributed machine learning technique that enables individual clients (e.g., user participants, edge devices, or organizations) to train a model on their local data in a secure environment and then share the trained model with an aggregator to build a global model collaboratively. In this work, we propose FedDefender, a defense mechanism against targeted poisoning attacks in FL by leveraging differential testing. FedDefender first applies differential testing on clients’ models using a synthetic input. Instead of comparing the output (predicted label), which is unavailable for synthetic input, FedDefender fingerprints the neuron activations of clients’ models to identify a potentially malicious client containing a backdoor. We evaluate FedDefender using MNIST and FashionMNIST datasets with 20 and 30 clients, and our results demonstrate that FedDefender effectively mitigates such attacks, reducing the attack success rate (ASR) to 10% without deteriorating the global model performance. 

   more » « less