A5114039207- Advanced Graph Neural Networks
- Graph Theory and Algorithms
- Brain Tumor Detection and Classification
- Neural Networks and Applications
- Evaluation and Optimization Models
- Text and Document Classification Technologies
- Spectroscopy and Chemometric Analyses
- Recommender Systems and Techniques
- Industrial Vision Systems and Defect Detection
- Complex Network Analysis Techniques
- Fault Detection and Control Systems
Beijing University of Chemical Technology
2024-2025
Beijing Normal University
2022
With the increasing complexity of industrial systems, modeling and intelligent diagnosis high-dimensional data have become increasingly challenging. To address this issue, study proposes an optimal sparse principal component analysis (OSPCA) method with a varying regularization coefficient. The lower bound coefficient for achieving feature selection is given, theoretical proof provided. Subsequently, iterative optimization algorithm proposed model optimization. OSPCA are applied to...
Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness in various graph representation learning tasks. However, most existing GNNs focus primarily on capturing local information through explicit convolution, often neglecting global message-passing. This limitation hinders the establishment of a collaborative interaction between and information, which is crucial for comprehensively understanding data. To address these challenges, we propose novel framework called...
Multiview subspace clustering (MSC) maximizes the utilization of complementary description information provided by multiview data and achieves impressive performance. However, most them are inefficient or even invalid among large-scale scenarios due to expensive computational complexity. Recently, anchor strategy has been developed address this, which selects a few representative samples as points for representation learning graph construction. only explore single cross-view correlation,...
As a powerful model for deep learning on graph-structured data, the scalability limitation of Graph Neural Networks (GNNs) are receiving increasing attention. To tackle this limitation, two categories scalable GNNs have been proposed: sampling-based and simplification methods. However, methods suffer from high communication costs poor performance due to sampling process. Conversely, existing only rely parameter-free feature propagation, disregarding its spectral properties. Consequently,...
Banks are an important financial support for national economic development. It can adjust the market economy, industrial structure, raise funds construction, and provide loans to enterprises individuals who short of funds. With downward pressure pressure, some banks' liabilities higher than assets. accumulation time, cannot be repaid, finally they only end up in bankruptcy. Compared with domestic banks, phenomenon international bank bankruptcy is more serious. In order reduce occurrence such...