Search Results for author: Soung Chang Liew

Found 18 papers, 4 papers with code

Rephrase and Contrast: Fine-Tuning Language Models for Enhanced Understanding of Communication and Computer Networks

no code implementations21 Sep 2024 Liujianfu Wang, Yuyang Du, Jingqi Lin, Kexin Chen, Soung Chang Liew

Large language models (LLMs) are being widely researched across various disciplines, with significant recent efforts focusing on adapting LLMs for understanding of how communication networks operate.

Data Augmentation

GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits

no code implementations19 Aug 2024 Gongpu Chen, Soung Chang Liew, Deniz Gunduz

GINO-Q mitigates the curse of dimensionality by decomposing the RMAB into a series of subproblems, each with the same dimension as a single arm, ensuring that complexity increases linearly with the number of arms.

Multi-Armed Bandits Q-Learning

LLMind: Orchestrating AI and IoT with LLM for Complex Task Execution

no code implementations14 Dec 2023 Hongwei Cui, Yuyang Du, Qun Yang, Yulin Shao, Soung Chang Liew

Task-oriented communications are an important element in future intelligent IoT systems.

AI Agent

The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms

no code implementations14 Jul 2023 Yuyang Du, Hongyu Deng, Soung Chang Liew, Kexin Chen, Yulin Shao, He Chen

We begin by exploring LLM-assisted code refactoring, reuse, and validation, using an open-source software-defined radio (SDR) project as a case study.

In-Context Learning Scheduling

Efficient FFT Computation in IFDMA Transceivers

no code implementations5 Mar 2022 Yuyang Du, Soung Chang Liew, Yulin Shao

Our experimental results indicate that when the number of hardware processors is a power of two: 1) MPS-FFT has near-optimal computation time; 2) MPS-FFT incurs less than 44. 13\% of the computation time of the conventional pipelined FFT.

Scheduling

Bayesian Over-The-Air Computation

no code implementations8 Sep 2021 Yulin Shao, Deniz Gunduz, Soung Chang Liew

In the low signal-to-noise ratio (SNR) regime, the LMMSE estimator reduces the mean squared error (MSE) by at least 6 dB; in the high SNR regime, the LMMSE estimator lowers the error floor of MSE by 86. 4%; 2) For the asynchronous OAC, our LMMSE and sum-product maximum a posteriori (SP-MAP) estimators are on an equal footing in terms of the MSE performance, and are significantly better than the ML estimator.

Edge-computing

Denoising Noisy Neural Networks: A Bayesian Approach with Compensation

1 code implementation22 May 2021 Yulin Shao, Soung Chang Liew, Deniz Gunduz

Deep neural networks (DNNs) with noisy weights, which we refer to as noisy neural networks (NoisyNNs), arise from the training and inference of DNNs in the presence of noise.

Denoising Quantization

Federated Edge Learning with Misaligned Over-The-Air Computation

1 code implementation26 Feb 2021 Yulin Shao, Deniz Gunduz, Soung Chang Liew

Over-the-air computation (OAC) is a promising technique to realize fast model aggregation in the uplink of federated edge learning.

Flow Sampling: Network Monitoring in Large-Scale Software-Defined IoT Networks

no code implementations21 Jul 2020 Yulin Shao, Soung Chang Liew, He Chen, Yuyang Du

Software-defined Internet-of-Things networking (SDIoT) greatly simplifies the network monitoring in large-scale IoT networks by per-flow sampling, wherein the controller keeps track of all the active flows in the network and samples the IoT devices on each flow path to collect real-time flow statistics.

Multi-Agent Deep Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks with Imperfect Channels

1 code implementation25 Mar 2020 Yiding Yu, Soung Chang Liew, Taotao Wang

This paper aims to design a distributed deep reinforcement learning (DRL) based MAC protocol for a particular network, and the objective of this network is to achieve a global $\alpha$-fairness objective.

Networking and Internet Architecture

Sporadic Ultra-Time-Critical Crowd Messaging in V2X

no code implementations4 Mar 2020 Yulin Shao, Soung Chang Liew, Jiaxin Liang

To circumvent potential inefficiency arising from sporadicity, we propose an override network architecture whereby warning messages are delivered on the spectrum of the ordinary vehicular messages.

When Blockchain Meets AI: Optimal Mining Strategy Achieved By Machine Learning

no code implementations29 Nov 2019 Taotao Wang, Soung Chang Liew, Shengli Zhang

Experimental results indicate that, without knowing the parameter values of the mining MDP model, our multi-dimensional RL mining algorithm can still achieve the optimal performance over time-varying blockchain networks.

Cryptography and Security

New Transceiver Designs for Interleaved Frequency Division Multiple Access

no code implementations23 Nov 2019 Soung Chang Liew, Yulin Shao

For flexible resource allocation, this paper puts forth a new IFDMA resource allocation framework called Multi-IFDMA, in which a user can be allocated multiple IFDMA streams.

Carrier-Sense Multiple Access for Heterogeneous Wireless Networks Using Deep Reinforcement Learning

no code implementations16 Oct 2018 Yiding Yu, Soung Chang Liew, Taotao Wang

In particular, in a heterogeneous environment with nodes adopting different MAC protocols (e. g., CS-DLMA, TDMA, and ALOHA), a CS-DLMA node can learn to maximize the sum throughput of all nodes.

Networking and Internet Architecture

AlphaSeq: Sequence Discovery with Deep Reinforcement Learning

no code implementations26 Sep 2018 Yulin Shao, Soung Chang Liew, Taotao Wang

We demonstrate the searching capabilities of AlphaSeq in two applications: 1) AlphaSeq successfully rediscovers a set of ideal complementary codes that can zero-force all potential interferences in multi-carrier CDMA systems.

Deep Reinforcement Learning reinforcement-learning +1

Sparsity Learning Based Multiuser Detection in Grant-Free Massive-Device Multiple Access

no code implementations28 Jul 2018 Tian Ding, Xiaojun Yuan, Soung Chang Liew

In this work, we study the multiuser detection (MUD) problem for a grant-free massive-device multiple access (MaDMA) system, where a large number of single-antenna user devices transmit sporadic data to a multi-antenna base station (BS).

User Identification

Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks

1 code implementation1 Dec 2017 Yiding Yu, Taotao Wang, Soung Chang Liew

In particular, the use of neural networks in DRL (as opposed to traditional reinforcement learning) allows for fast convergence to optimal solutions and robustness against perturbation in hyper-parameter settings, two essential properties for practical deployment of DLMA in real wireless networks.

Networking and Internet Architecture

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