Jin Li

Orcid: 0000-0003-3332-7790

Affiliations:
  • Hong Kong University of Science and Technology, Guangzhou, China
  • Fuzhou University, College of Computer and Data Science, China


According to our database1, Jin Li authored at least 12 papers between 2023 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Curriculum-guided graph self-augmentation: A progressive deepening framework for GNNs.
Neural Networks, 2026

UniTrain: A universal iterative semi-supervised training framework for graph representation learning.
Neural Networks, 2026

Feature space variation-based active learning sample query strategy for graph deep learning.
Expert Syst. Appl., 2026

2025
Another Perspective of Over-Smoothing: Alleviating Semantic Over-Smoothing in Deep GNNs.
IEEE Trans. Neural Networks Learn. Syst., April, 2025

GSSCL: A framework for Graph Self-Supervised Curriculum Learning based on clustering label smoothing.
Neural Networks, 2025

Enhanced Graph Transformer: Multi-scale attention with Heterophilous Curriculum Augmentation.
Knowl. Based Syst., 2025

2024
DWSSA: Alleviating over-smoothness for deep Graph Neural Networks.
Neural Networks, 2024

Training Graph Transformers via Curriculum-Enhanced Attention Distillation.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

HopMAE: Self-supervised Graph Masked Auto-Encoders from a Hop Perspective.
Proceedings of the Advanced Intelligent Computing Technology and Applications, 2024

Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-Smoothness in Deep GNNs.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Semi-Supervised Node Classification via Semi-Global Graph Transformer Based on Homogeneity Augmentation.
Parallel Process. Lett., 2023

Graph Contrastive Representation Learning with Input-Aware and Cluster-Aware Regularization.
Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023


  Loading...