A5050700559- Advanced Graph Neural Networks
- Extremum Seeking Control Systems
- EEG and Brain-Computer Interfaces
- Advanced Radiotherapy Techniques
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Epigenetics and DNA Methylation
- Topic Modeling
- Radiomics and Machine Learning in Medical Imaging
- Advances in Oncology and Radiotherapy
- Iterative Learning Control Systems
Sun Yat-sen University
2023-2024
Dalian University of Technology
2024
The last years have witnessed the emergence of a promising self-supervised learning strategy, referred to as masked autoencoding. However, there is lack theoretical understanding how masking matters on graph autoencoders (GAEs). In this work, we present autoencoder (MaskGAE), framework for graph-structured data. Different from standard GAEs, MaskGAE adopts modeling (MGM) principled pretext task - portion edges and attempting reconstruct missing part with partially visible, unmasked...
Graph contrastive learning (GCL) has emerged as a representative paradigm in graph self-supervised learning, where negative samples are commonly regarded the key to preventing model collapse and producing distinguishable representations. Recent studies have shown that GCL without can achieve state-of-the-art performance well scalability improvement, with bootstrapped latent (BGRL) prominent step forward. However, BGRL relies on complex architecture maintain ability scatter representations,...
Differential equations offer a foundational yet powerful framework for modeling interactions within complex dynamic systems and are widely applied across numerous scientific fields. One common challenge in this area is estimating the unknown parameters of these relationships. However, traditional numerical optimization methods rely on selection initial parameter values, making them prone to local optima. Meanwhile, deep learning Bayesian require training models specific differential...