8 papers
Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained Programming
Ziwen Liu, Yan Liu, Congying Han +3
Chance-constrained programs (CCPs) optimize decisions under uncertainty by limiting the probability of constraint violation. Despite advances in traditional and learning-based appr…
Sampling from Binary Quadratic Distributions via Stochastic Localization
Chenguang Wang, Kaiyuan Cui, Weichen Zhao +1
Sampling from binary quadratic distributions (BQDs) is a fundamental but challenging problem in discrete optimization and probabilistic inference. Previous work established theoret…
Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage
Chenguang Wang, Xiaoyu Zhang, Kaiyuan Cui +3
Training neural samplers directly from unnormalized densities without access to target distribution samples presents a significant challenge. A critical desideratum in these settin…
FlexiDrop: Theoretical Insights and Practical Advances in Random Dropout Method on GNNs
Zhiheng Zhou, Sihao Liu, Weichen Zhao
Graph Neural Networks (GNNs) are powerful tools for handling graph-type data. Recently, GNNs have been widely applied in various domains, but they also face some issues, such as ov…
Graph Neural Aggregation-diffusion with Metastability
Kaiyuan Cui, Xinyan Wang, Zicheng Zhang +1
Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs). Due to the connection between graph diffusion and mes…
Understanding Oversmoothing in Diffusion-Based GNNs From the Perspective of Operator Semigroup Theory
Weichen Zhao, Chenguang Wang, Xinyan Wang +3
This paper presents an analytical study of the oversmoothing issue in diffusion-based Graph Neural Networks (GNNs). Generalizing beyond extant approaches grounded in random walk an…
Improved Naive Bayes with Mislabeled Data
Qianhan Zeng, Yingqiu Zhu, Xuening Zhu +5
Labeling mistakes are frequently encountered in real-world applications. If not treated well, the labeling mistakes can deteriorate the classification performances of a model serio…
Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective
Weichen Zhao, Chenguang Wang, Congying Han +1
The over-smoothing problem is an obstacle of developing deep graph neural network (GNN). Although many approaches to improve the over-smoothing problem have been proposed, there is…