Yexiong Lin

According to our database, Yexiong Lin authored at least 6 papers between 2021 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Improving the Instance-Dependent Transition Matrix Estimation by Exploiting Self-Supervised Learning.

Yexiong Lin, Yu Yao, Zhaoqing Wang, Xu Shen, Jun Yu, Bo Han, Tongliang Liu

IEEE Trans. Pattern Anal. Mach. Intell., November, 2025

Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching.

Yexiong Lin, Yu Yao, Tongliang Liu

CoRR, May, 2025

2024

Learning the Latent Causal Structure for Modeling Label Noise.

Yexiong Lin, Yu Yao, Tongliang Liu

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation.

Yexiong Lin, Yu Yao, Xiaolong Shi, Mingming Gong, Xu Shen, Dong Xu, Tongliang Liu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Do We Need to Penalize Variance of Losses for Learning with Label Noise?

Yexiong Lin, Yu Yao, Yuxuan Du, Jun Yu, Bo Han, Mingming Gong, Tongliang Liu

CoRR, 2022

2021

Authenticity verification on social data outsourcing.

Haowen Chen, Qiang Qu, Yexiong Lin, Xia Chen, Keqin Li

Comput. Secur., 2021