한동준 교수

We consider federated learning (FL) with multiple wireless edge servers having their own local coverage. We focus on speeding up training in this increasingly practical setup. Our key idea is to utilize the clients located in the overlapping coverage areas among adjacent edge servers (ESs); in the model-downloading stage, the clients in the overlapping areas receive multiple models from different ESs, take the average of the received models, and then update the averaged model with their local da

Federated learning has been spotlighted as a way to train neural networks using distributed data with no need for individual nodes to share data. Unfortunately, it has also been shown that adversaries may be able to extract local data contents off model parameters transmitted during federated learning. A recent solution based on the secure aggregation primitive enabled privacy-preserving federated learning, but at the expense of significant extra communication/computational resources. In this pa

A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can si

While network coverage maps continue to expand, many devices located in remote areas remain unconnected to terrestrial communication infrastructures, preventing them from getting access to the associated data-driven services. In this paper, we propose a ground-to-satellite cooperative federated learning (FL) methodology to facilitate machine learning service management over remote regions. Our methodology orchestrates satellite constellations to provide the following key functions during FL: (i)

The demand for intelligent services at the network edge has introduced several research challenges. One is the need for a machine learning architecture that achieves personalization (to individual clients) and generalization (to unseen data) properties concurrently across different applications. Another is the need for an inference strategy that can satisfy network resource and latency constraints during testing-time. Existing techniques in federated learning have encountered a steep trade-off b

In wireless distributed computing systems, mobile devices that are connected wirelessly to the Fog (e.g., small base stations) collaboratively solve a given computational task. Unfortunately, wireless distributed computing systems suffer from packet losses due to severe channel fading. Moreover, a wireless device can drop out of the system when leaving the coverage of a master node in the Fog layer. We model this unreliability between a device and a master node as a packet erasure channel. When

Coded computation is a framework which provides redundancy in distributed computing systems to speed up large-scale tasks. Although most existing works assume error-free scenarios, the link failures are common in current wired/wireless networks. In this paper, we consider the straggler problem in distributed computing systems with link failures, by modeling the links between the master node and worker nodes as packet erasure channels. We first analyze the latency in this setting using an (n, k)

Distributed learning plays a key role in reducing the training time of modern deep neural networks with massive datasets. In this article, we consider a distributed learning problem where gradient computation is carried out over a number of computing devices at the wireless edge. We propose hierarchical broadcast coding, a provable coding-theoretic framework to speed up distributed learning at the wireless edge. Our contributions are threefold. First, motivated by the hierarchical nature of real

Devices located in remote regions often lack coverage from well-developed terrestrial communication infrastructure. This not only prevents them from experiencing high quality communication services but also hinders the delivery of machine learning services in remote regions. In this paper, we propose a new federated learning (FL) methodology tailored to space-air-ground integrated networks (SAGINs) to tackle this issue. Our approach strategically leverages the nodes within space and air layers a

This paper investigates spectral shaping of multi-carrier-modulation waveforms based on combination of Nyquist windowing and subband filtering. The combined windowing/filtering allows simultaneous control on both subcarrier and subband spectra. When compared with the existing Nyquist windowing or subband filtering techniques under a fixed excess frame length constraint, the proposed scheme offers reduced sensitivity to carrier frequency and symbol timing offsets. Establishing an analytical tool

A fundamental challenge to providing edge-AI services is the need for a machine learning (ML) model that achieves personalization (i.e., to individual clients) and generalization (i.e., to unseen data) properties concurrently. Existing techniques in federated learning (FL) have encountered a steep tradeoff between these objectives and impose large computational requirements on edge devices during training and inference. In this paper, we propose SplitGP, a new split learning solution that can si

The aerial imagery captured by unmanned aerial vehicles (UAVs) exhibits several challenging characteristics such as large variations in object size and complex backgrounds, which make it difficult for existing detectors to detect small objects in such imagery. To address the problem of false or missed detections of small objects in UAV imagery, the BHF-YOLOv5 detection model is proposed. Firstly, the Biformer module is added to the backbone network, which employs sparse sampling to retain fine-g

In low-latency applications for 5G and beyond, precise synchronization becomes more challenging. In this correspondence, we generalized the analytical tool to design combined window-filter waveform, which can tolerate imperfect synchronization scenarios. Compared to the previous work focusing on an ideal channel, the generalized tool considers the effect of multipath fading with instantaneous or statistical channel state information at the transmitter (CSIT). The waveform designed by the propose

Distributed antenna system (DAS) has been deployed for over a decade. DAS has advantages in capacity especially for the cell edge users, in both single-cell and multi-cell environments. In this paper, non-orthogonal multiple access (NOMA) is suggested in single-cell DAS to maximize user fairness and sumrate. Two transmission strategies are considered: NOMA with single selection transmission and NOMA with blanket transmission. In a two-user scenario, the center base station (BS) uses NOMA to serv

As the size of a model increases, making predictions using deep neural networks (DNNs) is becoming more computationally expensive. Multi-exit neural network is one promising solution that can flexibly make anytime predictions via early exits, depending on the current test-time budget which may vary over time in practice (e.g., self-driving cars with dynamically changing speeds). However, the prediction performance at the earlier exits is generally much lower than the final exit, which becomes a