Hao Sun

Orcid: 0000-0002-4645-2999

Affiliations:
  • Beijing University of Posts and Telecommunications, China


According to our database1, Hao Sun authored at least 12 papers between 2017 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
LightSAM: Parameter-Agnostic Sharpness-Aware Minimization.
CoRR, May, 2025

2024
AdaSAM: Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networks.
Neural Networks, January, 2024

Hierarchical Graph Interaction Transformer With Dynamic Token Clustering for Camouflaged Object Detection.
IEEE Trans. Image Process., 2024

2023
Efficient Federated Learning Via Local Adaptive Amended Optimizer With Linear Speedup.
IEEE Trans. Pattern Anal. Mach. Intell., December, 2023

On the Guaranteed Almost Equivalence Between Imitation Learning From Observation and Demonstration.
IEEE Trans. Neural Networks Learn. Syst., February, 2023

FedLALR: Client-Specific Adaptive Learning Rates Achieve Linear Speedup for Non-IID Data.
CoRR, 2023

2022
Lossy Compression of Communication Traces Using Recurrent Neural Networks.
IEEE Trans. Parallel Distributed Syst., 2022

2021
Performance Analysis of Graph Neural Network Frameworks.
Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, 2021

DSP-PIGAN: A Precision-Consistency Machine Learning Algorithm for Solving Partial Differential Equations.
Proceedings of the ICMLC 2021: 13th International Conference on Machine Learning and Computing, 2021

2020
Fast Training of POI Recommendation Models Using Gradient Compression.
Proceedings of the Spatial Data and Intelligence - First International Conference, 2020

2018
Students performance modeling based on behavior pattern.
J. Ambient Intell. Humaniz. Comput., 2018

2017
Poor performance discovery of college students based on behavior pattern.
Proceedings of the 2017 IEEE SmartWorld, 2017


  Loading...