X
Xiaoheng Deng
Researcher at Central South University
Publications - 125
Citations - 1537
Xiaoheng Deng is an academic researcher from Central South University. The author has contributed to research in topics: Computer science & Edge computing. The author has an hindex of 15, co-authored 94 publications receiving 863 citations. Previous affiliations of Xiaoheng Deng include South University & Hunan University of Technology.
Papers
More filters
Proceedings ArticleDOI
A Range Query Technology for Structured P2P Network
Xiaoheng Deng,Dao-de He,Yi Liu +2 more
TL;DR: This paper proposes a resources allocating mechanism for searching the objects among certain ranges in P2P network, and gives the searching algorithm in detail.
Proceedings ArticleDOI
Poster: Reliable On-Ramp Merging via Multimodal Reinforcement Learning
TL;DR: In this article , the authors outline ongoing research ideas for reliable and autonomous on-ramp merging assisted by vehicular communications, by jointly leveraging the basic safety messages from neighboring vehicles and the surveillance images, a merging vehicle can perform reliable driving via robust multimodal RL.
Proceedings ArticleDOI
Towards Scale Adaptive Underwater Detection Through Refined Pyramid Grid
TL;DR: In this paper , a refined pyramid grid (RPG) was proposed to improve the performance of underwater object detection, and a Harmonizing Focal Loss (HFL) was also proposed to generalize the discrete labels in focal loss to the continuous version.
Proceedings ArticleDOI
Efficient Privacy Preserving Graph Neural Network for Node Classification
TL;DR: In this paper , a privacy-preserving graph neural network (GNN) was developed to enforce differential privacy in GNNs, which utilizes a private functional mechanism (FM) to train the learning model.
Journal ArticleDOI
Multirelational Collaborative Filtering for Global Graph Neural Networks to Mine Evolutional Social Relations
TL;DR: Wang et al. as discussed by the authors integrated the collaborative and the sequential relations into an end-to-end graph neural network (GNN) simultaneously and proposed a novel framework, namely multirelational collaborative filtering (MRCF), to explore the evolutional social relations.