YHYangshuo He

Yangshuo He

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yangshuo He has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Robustness in Wireless Distributed Learning: An Information-Theoretic Analysis

    by Yangshuo He, Guanding Yu, Huaiyu Dai

    In recent years, the application of artificial intelligence (AI) in wireless communications has demonstrated inherent robustness against wireless channel distortions. Most existing works empirically leverage this robustness to yield considerable performance gains through AI architectural designs. However, there is a lack of direct theoretical analysis of this robustness and its potential to enhance communication efficiency, which restricts the full exploitation of these advantages. In this paper, we adopt an information-theoretic approach to evaluate the robustness in wireless distributed learning by deriving an upper bound on the task performance loss due to imperfect wireless channels. Utilizing this insight, we define task outage probability and characterize the maximum transmission rate under task accuracy guarantees, referred to as the task-aware ϵ-capacity resulting from the robustness. To achieve the utility of the theoretical results in practical settings, we present an efficient algorithm for the approximation of the upper bound. Subsequently, we devise a robust training framework that optimizes the trade-off between robustness and task accuracy, enhancing the robustness against channel distortions. Extensive experiments validate the effectiveness of the proposed upper bound and task-aware ϵ-capacity and demonstrate that the proposed robust training framework achieves high robustness, thus ensuring a high transmission rate while maintaining inference performance.


  • Semantic Feature Scheduling and Rate Control in Multi-Modal Distributed Network

    by Huiguo Gao, Guanding Yu, Yangshuo He, 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.


  • Rate-Adaptive Coding Mechanism for Semantic Communications With Multi-Modal Data

    by Yangshuo He, Guanding Yu, Yunlong Cai

    Recently, the ever-increasing demand for bandwidth in multi-modal communication systems requires a paradigm shift. Powered by deep learning, semantic communications are applied to multi-modal scenarios to boost communication efficiency and save communication resources. However, the existing end-to-end neural network (NN) based framework without the channel encoder/decoder is incompatible with modern digital communication systems. Moreover, most end-to-end designs are task-specific and require re-design and re-training for new tasks, which limits their applications. In this paper, we propose a distributed multi-modal semantic communication framework incorporating the conventional channel encoder/decoder. We adopt NN-based semantic encoder and decoder to extract correlated semantic information contained in different modalities, including speech, text, and image. Based on the proposed framework, we further establish a general rate-adaptive coding mechanism for various types of multi-modal semantic tasks. In particular, we utilize unequal error protection based on semantic importance, which is derived by evaluating the distortion bound of each modality. We further formulate and solve an optimization problem that aims at minimizing inference delay while maintaining inference accuracy for semantic tasks. Numerical results show that the proposed mechanism fares better than both conventional communication and existing semantic communication systems in terms of task performance, inference delay, and deployment complexity.


  • A Customized NoC Architecture to Enable Highly Localized Computing-on-the-Move DNN Dataflow

    by Kaining Zhou, Yangshuo He, Rui Xiao, Jiayi Liu, Kejie Huang

    The ever-increasing computation complexity of fast-growing Deep Neural Networks (DNNs) has requested new computing paradigms to overcome the memory wall in conventional Von Neumann computing architectures. The emerging Computing-In-Memory (CIM) architecture has been a promising candidate to accelerate neural network computing. However, data movement between CIM arrays may still dominate the total power consumption in conventional designs. This brief proposes a flexible CIM processor architecture named Domino and “Computing-On-the-Move” (COM) dataflow, to enable stream computing and local data access to significantly reduce data movement energy. Meanwhile, Domino employs customized distributed instruction scheduling within Network-on-Chip (NoC) to implement inter-memory computing and attain mapping flexibility. The evaluation with prevailing DNN models shows that Domino achieves 1.77-to- $2.37\times $ power efficiency over several state-of-the-art CIM accelerators and improves the throughput by 1.28-to- $13.16\times $ .