Search Results for author: Kaibin Huang

Found 25 papers, 1 papers with code

Vertical Layering of Quantized Neural Networks for Heterogeneous Inference

no code implementations10 Dec 2022 Hai Wu, Ruifei He, Haoru Tan, Xiaojuan Qi, Kaibin Huang

Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width.


Task-Oriented Over-the-Air Computation for Multi-Device Edge AI

no code implementations2 Nov 2022 Dingzhu Wen, Xiang Jiao, Peixi Liu, Guangxu Zhu, Yuanming Shi, Kaibin Huang

To design inference-oriented AirComp, the transmit precoders at edge devices and receive beamforming at edge server are jointly optimized to rein in the aggregation error and maximize the inference accuracy.

Decision Making

In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks

no code implementations7 Oct 2022 Kaibin Huang, Hai Wu, Zhiyan Liu, Xiaojuan Qi

We further propose a virtualized 6G network architecture customized for deploying in-situ model downloading with the key feature of a three-tier (edge, local, and central) AI library.

Realizing Ultra-Fast and Energy-Efficient Baseband Processing Using Analogue Resistive Switching Memory

no code implementations7 May 2022 Qunsong Zeng, Jiawei Liu, Jun Lan, Yi Gong, Zhongrui Wang, Yida Li, Kaibin Huang

To support emerging applications ranging from holographic communications to extended reality, next-generation mobile wireless communication systems require ultra-fast and energy-efficient (UFEE) baseband processors.

Accelerating Federated Edge Learning via Topology Optimization

no code implementations1 Apr 2022 Shanfeng Huang, Zezhong Zhang, Shuai Wang, Rui Wang, Kaibin Huang

In this paper, a novel topology-optimized federated edge learning (TOFEL) scheme is proposed to tackle the heterogeneity issue in federated learning and to improve the communication-and-computation efficiency.

3D Object Detection Federated Learning +3

Over-the-Air Aggregation for Federated Learning: Waveform Superposition and Prototype Validation

no code implementations27 Oct 2021 Huayan Guo, Yifan Zhu, Haoyu Ma, Vincent K. N. Lau, Kaibin Huang, Xiaofan Li, Huabin Nong, Mingyu Zhou

In this paper, we develop an orthogonal-frequency-division-multiplexing (OFDM)-based over-the-air (OTA) aggregation solution for wireless federated learning (FL).

Federated Learning

Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devices

no code implementations30 Sep 2021 Dingzhu Wen, Ki-Jun Jeon, Kaibin Huang

To tackle the challenge, in this paper, a federated dropout (FedDrop) scheme is proposed building on the classic dropout scheme for random model pruning.

Federated Learning

Turning Channel Noise into an Accelerator for Over-the-Air Principal Component Analysis

no code implementations20 Apr 2021 Zezhong Zhang, Guangxu Zhu, Rui Wang, Vincent K. N. Lau, Kaibin Huang

The novelty of this design lies in exploiting channel noise to accelerate the descent in the region around each saddle point encountered by gradient descent, thereby increasing the convergence speed of over-the-air PCA.

Data Compression

An Energy-efficient Aerial Backhaul System with Reconfigurable Intelligent Surface

no code implementations5 Apr 2021 Hong-Bae Jeon, Sung-Ho Park, Jaedon Park, Kaibin Huang, Chan-Byoung Chae

In this paper, we propose a novel wireless architecture, mounted on a high-altitude aerial platform, which is enabled by reconfigurable intelligent surface (RIS).

Wirelessly Powered Federated Edge Learning: Optimal Tradeoffs Between Convergence and Power Transfer

no code implementations24 Feb 2021 Qunsong Zeng, Yuqing Du, Kaibin Huang

To derive guidelines on deploying the resultant wirelessly powered FEEL (WP-FEEL) system, this work aims at the derivation of the tradeoff between the model convergence and the settings of power sources in two scenarios: 1) the transmission power and density of power-beacons (dedicated charging stations) if they are deployed, or otherwise 2) the transmission power of a server (access-point).

Reconfigurable Intelligent Surface Assisted Mobile Edge Computing with Heterogeneous Learning Tasks

no code implementations25 Dec 2020 Shanfeng Huang, Shuai Wang, Rui Wang, Miaowen Wen, Kaibin Huang

The ever-growing popularity and rapid improving of artificial intelligence (AI) have raised rethinking on the evolution of wireless networks.

3D Object Detection Autonomous Driving +2

Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels

no code implementations8 Oct 2020 Dingzhu Wen, Ki-Jun Jeon, Mehdi Bennis, Kaibin Huang

Targeting broadband channels, we consider the joint control of parameter allocation, sub-channel allocation, and transmission power to improve the performance of PARTEL.

Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computing

no code implementations14 Jul 2020 Qunsong Zeng, Yuqing Du, Kaibin Huang, Kin K. Leung

Among others, the framework of federated edge learning (FEEL) is popular for its data-privacy preservation.

Information Theory Signal Processing Information Theory

Scheduling for Cellular Federated Edge Learning with Importance and Channel Awareness

no code implementations1 Apr 2020 Jinke Ren, Yinghui He, Dingzhu Wen, Guanding Yu, Kaibin Huang, Dongning Guo

In this paper, a novel scheduling policy is proposed to exploit both diversity in multiuser channels and diversity in the "importance" of the edge devices' learning updates.


Joint Parameter-and-Bandwidth Allocation for Improving the Efficiency of Partitioned Edge Learning

no code implementations10 Mar 2020 Dingzhu Wen, Mehdi Bennis, Kaibin Huang

To this end, in each iteration, the model is dynamically partitioned into parametric blocks, which are downloaded to worker groups for updating using data subsets.

One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis

no code implementations16 Jan 2020 Guangxu Zhu, Yuqing Du, Deniz Gunduz, Kaibin Huang

We provide a comprehensive analysis of the effects of wireless channel hostilities (channel noise, fading, and channel estimation errors) on the convergence rate of the proposed FEEL scheme.

Information Theory Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Signal Processing Information Theory

An Introduction to Communication Efficient Edge Machine Learning

no code implementations3 Dec 2019 Qiao Lan, Zezhong Zhang, Yuqing Du, Zhenyi Lin, Kaibin Huang

The main theme in the area is to design new communication techniques and protocols for efficient implementation of different distributed learning frameworks (i. e., federated learning) in wireless networks.

Information Theory Signal Processing Information Theory

An Overview of Data-Importance Aware Radio Resource Management for Edge Machine Learning

no code implementations10 Nov 2019 Dingzhu Wen, Xiaoyang Li, Qunsong Zeng, Jinke Ren, Kaibin Huang

Specifically, the metrics that measure data importance in active learning (e. g., classification uncertainty and data diversity) are applied to RRM for efficient acquisition of distributed data in wireless networks to train AI models at servers.

Active Learning BIG-bench Machine Learning +1

High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning

no code implementations9 Oct 2019 Yuqing Du, Sheng Yang, Kaibin Huang

First, the framework features a practical hierarchical architecture for decomposing the stochastic gradient into its norm and normalized block gradients, and efficiently quantizes them using a uniform quantizer and a low-dimensional codebook on a Grassmann manifold, respectively.

Federated Learning Quantization

Energy-Efficient Radio Resource Allocation for Federated Edge Learning

no code implementations13 Jul 2019 Qunsong Zeng, Yuqing Du, Kin K. Leung, Kaibin Huang

To reduce devices' energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling.

Management Scheduling

Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)

no code implementations30 Dec 2018 Guangxu Zhu, Yong Wang, Kaibin Huang

To leverage the data and resources, a new machine learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing fast and intelligent services to mobile users.


Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission

no code implementations5 Dec 2018 Dongzhu Liu, Guangxu Zhu, Jun Zhang, Kaibin Huang

To solve the problem, a new retransmission protocol called data-importance aware automatic-repeat-request (importance ARQ) is proposed.

Towards an Intelligent Edge: Wireless Communication Meets Machine Learning

no code implementations2 Sep 2018 Guangxu Zhu, Dongzhu Liu, Yuqing Du, Changsheng You, Jun Zhang, Kaibin Huang

Accordingly, a new research area, called edge learning, emerges, which crosses and revolutionizes two disciplines: wireless communication and machine learning.

BIG-bench Machine Learning Edge-computing

Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning

1 code implementation7 Aug 2018 Jiayao Zhang, Guangxu Zhu, Robert W. Heath Jr., Kaibin Huang

We hope to inspire practitioners in different fields to adopt the powerful tool of Grassmannian learning in their research.

Cannot find the paper you are looking for? You can Submit a new open access paper.