A5001581968- Topic Modeling
- Advanced Graph Neural Networks
- Bacteriophages and microbial interactions
- Machine Learning in Bioinformatics
- Complex Network Analysis Techniques
- Chemical Synthesis and Analysis
- Cytomegalovirus and herpesvirus research
- Genomics and Phylogenetic Studies
- Caching and Content Delivery
- Nanoplatforms for cancer theranostics
- Analytical Chemistry and Chromatography
- Computational Drug Discovery Methods
South China Normal University
2022-2025
Tianjin University
2021
Abstract Language models have shown the capacity to learn complex molecular distributions. In field of generation, they are designed explore distribution molecules, and previous studies demonstrated their ability molecule sequences. early times, recurrent neural networks (RNNs) were widely used for feature extraction from sequence data been various generation tasks. recent years, attention mechanism has become popular. It captures underlying relationships between words is applied language...
Background: The application of deep generative models for molecular discovery has witnessed a significant surge in recent years. Currently, the field generation and optimization is predominantly governed by autoregressive regardless how data represented. However, an emerging paradigm domain diffusion models, which treat non-autoregressively have achieved breakthroughs areas such as image generation. Methods: potential capability tasks remain largely unexplored. In order to investigate...
A <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -core is the special cohesive subgraph where each vertex has at least degree. It widely used in graph mining applications such as community detection, visualization, and clique discovery. Because dynamic graphs frequently evolve, obtaining their -cores via decomposition inefficient. Instead, previous studies proposed various methods for updating based on inserted (removed) edges. Unfortunately, parallelism of...