A5023446235- Cancer-related molecular mechanisms research
- Multimodal Machine Learning Applications
- Domain Adaptation and Few-Shot Learning
- Bayesian Modeling and Causal Inference
- Internet Traffic Analysis and Secure E-voting
- Advanced Causal Inference Techniques
- Morphological variations and asymmetry
- Neural Networks and Applications
- Point processes and geometric inequalities
- Statistical Methods and Inference
- AI-based Problem Solving and Planning
- Automated Road and Building Extraction
- Advanced Graph Neural Networks
- Caching and Content Delivery
- Wireless Networks and Protocols
Huawei Technologies (China)
2017-2025
Hong Kong University of Science and Technology
2025
University of Hong Kong
2025
Zhejiang University
2023
In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN).By leveraging cause-effect analysis, can discern edges based on asymmetric node dependency.The learned structure offers more accurate relationships among nodes.To reduce the computational complexity, introduce intervention-based graph learning.We first simplify analysis graphs by formulating it as structural learning model and define optimization...
Recently, Long Chain-of-Thoughts (CoTs) have gained widespread attention for improving the reasoning capabilities of Large Language Models (LLMs). This necessitates that existing LLMs, which lack ability to generate CoTs, acquire such capability through post-training methods. Without additional training, LLMs typically enhance their mathematical abilities inference scaling methods as MCTS. However, they are hindered by large action space and inefficient search strategies, making it...
Learning causal structure among event types on multitype sequences is an important but challenging task. Existing methods, such as the Multivariate Hawkes processes, mostly assumed that each sequence independent and identically distributed. However, in many real-world applications, it commonplace to encounter a topological network behind excited or inhibited not only by its history also neighbors. Consequently, failure describing dependency leads error detection of structure. By considering...
Domain generalization (DG) is a prevalent problem in real-world applications, which aims to train well-generalized models for unseen target domains by utilizing several source domains. Since domain labels, i.e., each data point sampled from, naturally exist, most DG algorithms treat them as kind of supervision information improve the performance. However, original labels may not be optimal signal due lack heterogeneity, diversity among For example, sample one closer another domain, its label...
Conditional independence (CI) testing is an important problem, especially in causal discovery. Most methods assume that all variables are fully observable and then test the CI among observed data. Such assumption often untenable beyond applications dealing with, e.g., psychological analysis about mental health status medical diagnosing (researchers need to consider existence of latent these scenarios); typically adopted schemes mainly suffer from robust or efficient issues. Accordingly, this...
Domain generalization (DG) is a prevalent problem in real-world applications, which aims to train well-generalized models for unseen target domains by utilizing several source domains. Since domain labels, i.e., each data point sampled from, naturally exist, most DG algorithms treat them as kind of supervision information improve the performance. However, original labels may not be optimal signal due lack heterogeneity, diversity among For example, sample one closer another domain, its label...
With the advent of cellular network technologies, mobile Internet access becomes norm in everyday life. In meantime, complaints made by subscribers about unsatisfactory also become increasingly frequent. From a operator's perspective, achieving accurate and timely diagnosis causes is critical for both improving subscriber-perceived experience maintaining robustness. We present Intelligent Customer Care Assistant (ICCA), distributed fault classification system that exploits data-driven...