Minh N. H. Nguyen
Title: Federated Learning: Towards Large-scale Distributed Learning Systems
Bio:
Minh N. H. Nguyen (M’20) received a BE degree in Computer Science and Engineering from Ho Chi Minh City University of Technology, Vietnam, in 2013 and a Ph.D. degree in Computer Science and Engineering from Kyung Hee University, South Korea, in 2020. He continued the research on Federated Learning and Democratized Learning with the PostDoc at Intelligent Networking lab, Kyung Hee University, South Korea till 2022. He is currently working as a lecturer and in charge of Research Program of Digital Science and Technology Institute at The University of Danang – Vietnam – Korea University of Information and Communication Technology, Vietnam. He received the best KHU Ph.D. thesis award in engineering in 2020. He had 13 publications in high-quality IEEE journals such as ACM/IEEE ToN, IEEE TWC, IEEE TNNLS, IEEE TMC, IEEE TVT, IEEE IoT, IEEE CM, IEEE CIM, etc., and INFOCOM conference. He participated as Track Chair and Session Chair for ATC 2023 and CITA2023 Conference. His research interests include wireless communications, federated learning, natural language processing, and computer vision.
Abstract:
Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems toward large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, federated learning (FL) lays out a novel learning mechanism for building distributed machine learning systems. FL enables a decentralized paradigm for multiple clients to collaboratively train a generalized global model without sharing their private data. In this talk, we cover various designs of FL to cope with different perspectives of FL systems. We first introduce the typical and practical settings of FL towards better generalization abilities of client models for realizing robust personalized Federated Learning (FL) systems, efficient model aggregation methods have been considered as a critical research objective. It is a challenging issue due to the consequences of non-i.i.d. properties of client’s data, often referred to as statistical heterogeneity and small local data samples from the various data distributions and having burden in communication resource and energy. Therefore, to develop robust generalized global and personalized models, conventional FL methods need to redesign the knowledge aggregation from biased local models while considering the huge divergence of learning parameters due to skewed client data. To achieve these objectives, we develop novel approaches to study the extent of knowledge transfer between the global model and local models regarding single task as well as multi-Machine learning task. In addition, we show the efficiency of advanced strategies for FL systems such as pretraining, clustering, lightweight model design, self-organizing hierarchical structure, optimal resource allocation and energy efficiency. To this end, FL exhibits a promising scheme for future personalized AI applications in global and personalized performance while guaranteeing user privacy.
Nguyen H. Tran
Title: Federated PCA on Grassmann Manifold for IoT Anomaly Detection
Bio:
Nguyen H. Tran received BS and PhD degrees (with best PhD thesis award), from HCMC University of Technology and Kyung Hee University, in electrical and computer engineering, in 2005 and 2011, respectively. His research group has special interests in Distributed compUting, optimizAtion, and machine Learning (DUAL group). He received several best paper awards, including IEEE ICC 2016, ACM MSWiM 2019, and KICS/IEEE JCN 2023. He receives the Korea NRF Funding for Basic Science and Research 2016-2023, ARC Discovery Project 2020-2023, and SOAR award 2022-2023. He serves as an Editor for several journals such as IEEE Transactions on Green Communications and Networking (2016-2020), IEEE Journal of Selected Areas in Communications 2020 in distributed machine learning/Federated Learning, and IEEE Transactions on Machine Learning in Communications Networking (2022-).
Abstract:
With the proliferation of Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion detection systems (ML-IDS) effectively employ supervised learning methods, they possess limitations such as the requirement for labelled data and challenges with high-dimensional data. Recent unsupervised ML-IDS approaches like AutoEncoders and Generative Adversarial Networks (GAN) offer alternative solutions but pose challenges in deployment onto resource-constrained IoT devices and in interpretability. To address these concerns, this paper proposes a novel federated unsupervised anomaly detection framework — FedPCA — that leverages Principle Component Analysis (PCA) and the Alternatives Directions Method Multipliers (ADMM) to learn common representations of distributed non-i.i.d. datasets. Building on the FedPCA framework, we propose two algorithms, FedPE in Euclidean space and FedPG on Grassmann manifolds, and analyze their convergence characteristics. Our approach enables real-time threat detection and mitigation at the device level, enhancing network resilience while ensuring privacy. Experimental results on the UNSW-NB15 and TON-IoT datasets show that our proposed methods offer performance in anomaly detection comparable to non-linear baselines, while providing significant improvements in communication and memory efficiency, underscoring their potential for securing IoT networks.