JLJiahui Li

Jiahui Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jiahui Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Spiking Semantic Communication for Feature Transmission with HARQ

    by Mengyang Wang, Jiahui Li, Mengyao Ma, Xiaopeng Fan

    In Collaborative Intelligence (CI), the Artificial Intelligence (AI) model is divided between the edge and the cloud, with intermediate features being sent from the edge to the cloud for inference. Several deep learning-based Semantic Communication (SC) models have been proposed to reduce feature transmission overhead and mitigate channel noise interference. Previous research has demonstrated that Spiking Neural Network (SNN)-based SC models exhibit greater robustness on digital channels compared to Deep Neural Network (DNN)-based SC models. However, the existing SNN-based SC models require fixed time steps, resulting in fixed transmission bandwidths that cannot be adaptively adjusted based on channel conditions. To address this issue, this paper introduces a novel SC model called SNN-SC-HARQ, which combines the SNN-based SC model with the Hybrid Automatic Repeat Request (HARQ) mechanism. SNN-SC-HARQ comprises an SNN-based SC model that supports the transmission of features at varying bandwidths, along with a policy model that determines the appropriate bandwidth. Experimental results show that SNN-SC-HARQ can dynamically adjust the bandwidth according to the channel conditions without performance loss.


  • Open Access

    SNN-SC: A Spiking Semantic Communication Framework for Feature Transmission

    by Mengyang Wang, Jiahui Li, Mengyao Ma, Xiaopeng Fan, Yonghong Tian

    In Collaborative Intelligence (CI), Artificial Intelligence (AI) models are split between edge devices and cloud. Features extracted from input on edge devices are transmitted to the cloud for subsequent tasks. Extracting task-related and compact information is critical when transmission bandwidth is limited. In this paper, we propose a task-oriented Semantic Communication (SC) framework (SNN-SC) to address this problem. In SC, only important information for downstream tasks is extracted and transmitted. However, most of the existing SC works only transmit analog information on the AWGN channel and cannot be directly used for digital channels. SNN-SC fills this gap by using Spiking Neural Networks (SNNs) to extract and transmit semantic information. Since the outputs of SNNs are binary spikes, SNN-SC can be directly applied to digital channels. In SNN-SC, a new spiking neuron is proposed to help the cloud recover binary semantic information into informative floating-point features. Furthermore, we improve the performance of SNN-SC by maximizing the entropy of the semantic information. We evaluate the performance of SNN-SC on different collaborative classification models, digital channels, and bandwidths. The experimental results show that SNN-SC is more robust than the CNN-based SC framework and separate source and channel coding method on digital channels.

  • Open Access

    Constellation Design for Deep Joint Source-Channel Coding

    by Mengyang Wang, Jiahui Li, Mengyao Ma, Xiaopeng Fan

    Deep learning-based joint source-channel coding (JSCC) has shown excellent performance in image and feature transmission. However, the output values of the JSCC encoder are continuous, which makes the constellation of modulation complex and dense. It is hard and expensive to design radio frequency chains for transmitting such full-resolution constellation points. In this paper, two methods of mapping the full-resolution constellation to finite constellation are proposed for real system implementation. The constellation mapping results of the proposed methods correspond to regular constellation and irregular constellation, respectively. We apply the methods to existing deep JSCC models and evaluate them on AWGN channels with different signal-to-noise ratios (SNRs). Experimental results show that the proposed methods outperform the traditional uniform quadrature amplitude modulation (QAM) constellation mapping method by only adding a few additional parameters.

  • Open Access

    Deep Joint Source-Channel Coding for Multi-Task Network

    by Mengyang Wang, Zhicong Zhang, Jiahui Li, Mengyao Ma, Xiaopeng Fan

    Multi-task learning (MTL) is an efficient way to improve the performance of related tasks by sharing knowledge. However, most existing MTL networks run on a single end and are not suitable for collaborative intelligence (CI) scenarios. In this work, we propose an MTL network with a deep joint source-channel coding (JSCC) framework, which allows operating under CI scenarios. We first propose a feature fusion based MTL network (FFMNet) for joint object detection and semantic segmentation. Compared with other MTL networks, FFMNet gets higher performance with fewer parameters. Then FFMNet is split into two parts, which run on a mobile device and an edge server respectively. The feature generated by the mobile device is transmitted through the wireless channel to the edge server. To reduce the transmission overhead of the intermediate feature, a deep JSCC network is designed. By combining two networks together, the whole model achieves 512x compression for the intermediate feature and a performance loss within 2% on both tasks. At last, by training with noise, the FFMNet with JSCC is robust to various channel conditions and outperforms the separate source and channel coding scheme.