8 papers
Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
Shuo Wang, Shunyang Huang, Jinghui Yuan +2
Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the…
Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer
Jinghui Yuan, Jiaxuan Zou, Shuo Wang +2
Matrix-based optimizers have demonstrated immense potential in training Large Language Models (LLMs), however, designing an ideal optimizer remains a formidable challenge. A superi…
Riemannian Optimization on Relaxed Indicator Matrix Manifold
Jinghui Yuan, Fangyuan Xie, Feiping Nie +1
The indicator matrix plays an important role in machine learning, but optimizing it is an NP-hard problem. We propose a new relaxation of the indicator matrix and prove that this r…
Dual-Bounded Nonlinear Optimal Transport for Size Constrained Min Cut Clustering
Fangyuan Xie, Jinghui Yuan, Feiping Nie +1
Min cut is an important graph partitioning method. However, current solutions to the min cut problem suffer from slow speeds, difficulty in solving, and often converge to simple so…
A Margin-Maximizing Fine-Grained Ensemble Method
Jinghui Yuan, Hao Chen, Renwei Luo +1
Ensemble learning has achieved remarkable success in machine learning, but its reliance on numerous base learners limits its application in resource-constrained environments. This…
Multi-Task Curriculum Graph Contrastive Learning with Clustering Entropy Guidance
Chusheng Zeng, Bocheng Wang, Jinghui Yuan +2
Recent advances in unsupervised deep graph clustering have been significantly promoted by contrastive learning. Despite the strides, most graph contrastive learning models face cha…