Huiguo Gao

Dr. Huiguo Gao

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2023 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
HGHuiguo Gao
Huiguo Gao
Guanding YuGuanding Yu
Guanding Yu
YCYunlong Cai
Yunlong Cai
Traditional adaptive modulation scheme aims to maximize the spectral efficiency by selecting the appropriate modulation scheme under the premise of perfect bit-level data transmission. However, in task-oriented semantic communication systems, imperfect transmission can still lead to a good inference performance of semantic tasks due to the error correction capability of neural networks. In this paper, we propose novel adaptive modulation and retransmission schemes to maximize the spectral efficiency while guaranteeing the performance of semantic tasks. Specifically, we first introduce the robustness verification problem in semantic communication systems to analyze the robustness of neural network inference. We then formulate and solve the modulation scheme selection problem constrained by a robustness probability threshold. Consequently, a novel adaptive modulation scheme is developed to maximize the spectral efficiency while guaranteeing the goal of semantic communication. We also develop a retransmission scheme using existing combining techniques to further increase the data rate under harsh channel conditions. Extensive simulations are performed in unencoded and encoded semantic communication systems to validate the effectiveness of the proposed schemes.

22 October 2024 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
HGHuiguo Gao
Huiguo Gao
Guanding YuGuanding Yu
Guanding Yu
YHYangshuo He
Yangshuo He
YLYuanwei Liu
Yuanwei Liu
Traditional scheduling algorithms make decisions based solely on the channel conditions, without considering the transmitted semantic content. However, in multi-modal semantic communication systems, there is redundancy and variance in the importance of semantic features across modalities for task performance. To address this issue, we propose a novel feature scheduling and error probability control scheme that balances channel diversity and semantic diversity in semantic communication systems. Specifically, we first introduce a semantic feature importance metric to measure each feature’s contribution to the inference performance of semantic task. Using this metric, we formulate and solve an optimization problem to reduce overall latency while guaranteeing semantic task performance. Our detailed analysis examines feature selection strategies and transmission rate optimization to illustrate scheduling decisions based on both channel fading and semantic content. Consequently, we develop both optimal and low-complexity feature transmission scheduling schemes based on the optimization solution. Extensive experiments over multi-modal semantic communication systems validate that the semantic feature importance metric can reveal the importance of features from different modalities and accordingly affect their transmission rate. Additionally, the proposed schemes significantly reduce the system latency compared to the traditional methods.

28 January 2022 in Sensors
Verified
Journal Article
Open access
PDF file
HGHuiguo Gao
Huiguo Gao
MLMengyuan Lee
Mengyuan Lee
Guanding YuGuanding Yu
Guanding Yu
ZZZhaolin Zhou
Zhaolin Zhou
As an emerging paradigm considering data privacy and transmission efficiency, decentralized learning aims to acquire a global model using the training data distributed over many user devices. It is a challenging problem since link loss, partial device participation, and non-independent and identically distributed (non-iid) data distribution would all deteriorate the performance of decentralized learning algorithms. Existing work may restrict to linear models or show poor performance over non-iid data. Therefore, in this paper, we propose a decentralized learning scheme based on distributed parallel stochastic gradient descent (DPSGD) and graph neural network (GNN) to deal with the above challenges. Specifically, each user device participating in the learning task utilizes local training data to compute local stochastic gradients and updates its own local model. Then, each device utilizes the GNN model and exchanges the model parameters with its neighbors to reach the average of resultant global models. The iteration repeats until the algorithm converges. Extensive simulation results over both iid and non-iid data validate the algorithm’s convergence to near optimal results and robustness to both link loss and partial device participation.

3 October 2023 in IEEE Network
Verified
Journal Article
Closed access
HGHuiguo Gao
Huiguo Gao
Guanding YuGuanding Yu
Guanding Yu
YCYunlong Cai
Yunlong Cai
Traditional rate adaptive mechanism aims to maximize spectral efficiency by choosing the optimal transmission under the premise of perfect bit-level data transmission. However, in semantic communication systems, imperfect bit transmission could still lead to good performance due to the error correction capability of neural networks. In this paper, we propose a novel rate adaptive mechanism to maximize spectral efficiency while guaranteeing the performance of semantic tasks. In order to analyze the robustness of neural network inference, we introduce the robustness verification problem in semantic communications. Then, we propose and solve the modulation scheme selection problem subject to the robustness probability threshold constraint. Afterwards, a rate adaptive mechanism with the optimal modulation scheme is proposed. Simulations are conducted to validate the effectiveness of the proposed scheme, followed by some important open challenges for future related work.

4 April 2025 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
GDGuangyao Ding
Guangyao Ding
HGHuiguo Gao
Huiguo Gao
SLShengli Liu
Shengli Liu
Guanding YuGuanding Yu
Guanding Yu
Recently, deep learning (DL)-based semantic communication has emerged as a promising technique for enhancing transmission efficiency in various tasks. By transmitting the extracted semantic features instead of the original data, the communication delay can be significantly reduced. In this work, we design a semantic communication technique for low-latency device-edge co-inference systems which supports multi-stage semantic feature transmission. To reduce the average inference delay, we develop a multi-stage edge inference scheme and the corresponding early stopping strategy with the proposed semantic communication network. The edge inference would be directly terminated if the inference result at any stage is regarded as reliable. We also develop an algorithm to jointly optimize the transmission duration and decision threshold for both the two-stage and multi-stage inference schemes, aiming at minimizing the average inference delay while satisfying the inference accuracy requirement. Simulation results show that the proposed multi-stage edge inference scheme with early stopping strategy can effectively reduce the average edge inference delay.

24 October 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
JZJiaying Zhang
Jiaying Zhang
QHQiushuo Hou
Qiushuo Hou
HGHuiguo Gao
Huiguo Gao
Guanding YuGuanding Yu
Guanding Yu
Sidelink relay technique is an effective technique for coverage enhancement and data rate improvement, which has recently achieved success in diversified wireless applications. The main bottleneck of applying sidelink to multiple-user multiple-input multiple-output (MU-MIMO) system is how to overcome interference among user equipments (UEs). In this paper, we consider an MU-MIMO relay network with both downlink and uplink UEs, where sidelink reuses the same resources of uplink UEs. To maximize the sum rate of downlink UEs, we propose a novel joint resource block allocation and beamforming design algorithm for the considered MU-MIMO relay network. Specifically, we first formulate an optimization problem with the constraint on the sum-rate degradation of uplink UEs. However, the formulated mixed integer nonlinear programming problem is NP-hard. In order to solve this problem, we first relax the discrete variables and then transform the continuous problem into a convex one based on the weighted minimum mean square error (WMMSE) algorithm. Meanwhile, we prove the equivalence between the aforementioned two problems. Finally, we utilize the block coordinate descent method to solve the transformed problem and obtain the resource block allocation and beamforming design. Simulation results validate the effectiveness of the proposed algorithm and demonstrate the importance of joint optimization.