activity
20172023
most citedEdge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing

100 citations · 271 across the 31 of their papers we have counts for

collaborators

31 papers

cs.CR2023

Chained-DP: Can We Recycle Privacy Budget?

Jingyi Li, Guangjing Huang, Liekang Zeng +2

Privacy-preserving vector mean estimation is a crucial primitive in federated analytics. Existing practices usually resort to Local Differentiated Privacy (LDP) mechanisms that inj…

cs.DC2023

BeeFlow: Behavior Tree-based Serverless Workflow Modeling and Scheduling for Resource-Constrained Edge Clusters

Ke Luo, Tao Ouyang, Zhi Zhou +1

Serverless computing has gained popularity in edge computing due to its flexible features, including the pay-per-use pricing model, auto-scaling capabilities, and multi-tenancy sup…

cs.DC2023

Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services

Liekang Zeng, Xu Chen, Peng Huang +3

Graph Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures.…

cs.LG2023★ 1 cited

Towards Carbon-Neutral Edge Computing: Greening Edge AI by Harnessing Spot and Future Carbon Markets

Huirong Ma, Zhi Zhou, Xiaoxi Zhang +1

Provisioning dynamic machine learning (ML) inference as a service for artificial intelligence (AI) applications of edge devices faces many challenges, including the trade-off among…

cs.DC2022★ 2 cited

GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers

Liekang Zeng, Chongyu Yang, Peng Huang +3

Edge intelligence has arisen as a promising computing paradigm for supporting miscellaneous smart applications that rely on machine learning techniques. While the community has ext…

cs.NI2022

TIPS: Transaction Inclusion Protocol with Signaling in DAG-based Blockchain

Canhui Chen, Xu Chen, Zhixuan Fang

Directed Acyclic Graph (DAG) is a popular approach to achieve scalability of blockchain networks. Due to its high efficiency in data communication and great scalability, DAG has be…