Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Link opens in a new tab
Search content at Hong Kong Baptist University
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
View Scopus Profile
Bo HAN, Prof
Associate Professor
,
Department of Computer Science
https://orcid.org/0000-0002-6338-0958
Email
bhanml
hkbu.edu
hk
Accepting PhD Students
2016
2027
Research activity per year
Overview
Fingerprint
Network
Projects / Grants
(21)
Research Output
(278)
Prizes / Awards
(10)
Activities
(7)
Similar Scholars
(6)
Supervised Work
(3)
Fingerprint
Dive into the research topics where Bo HAN is active. Topic labels come from the works of this scholar. Together they form a unique fingerprint.
Sort by:
Weight
Alphabetically
Computer Science
Large Language Model
100%
Deep Neural Network
66%
Out-of-Distribution Detection
65%
Federated machine learning
60%
Adversarial Machine Learning
59%
Transition Matrix
56%
Experimental Result
56%
Data Distribution
55%
Learning System
45%
Training Data
42%
Machine Learning
41%
Adversarial Robustness
38%
Semisupervised Learning
33%
Learning Framework
30%
Graph Neural Network
29%
Deep Learning Method
29%
Language Modeling
29%
Annotation
28%
Unlabeled Data
23%
World Application
22%
Adversarial Example
20%
Learning Algorithm
20%
Foundation Model
19%
Reinforcement Learning
19%
Risk Estimator
18%
Representation Learning
18%
Performance Model
18%
Data Heterogeneity
17%
Subgraphs
16%
Generalization Performance
16%
Training Process
16%
Zero-Shot Learning
15%
Artificial Intelligence
14%
Art Performance
14%
Self-Supervised Learning
14%
Probability
14%
Bilevel Optimisation
14%
Domain Adaptation
14%
Optimization Problem
14%
Regularization
13%
de-noising
13%
Contrastive Learning
13%
Generative Model
13%
Performance Gain
13%
Machine Learning Model
13%
Class Distribution
13%
Instance Level
13%
Effective Method
12%
Selection Process
12%
Classification Performance
12%
Keyphrases
Label Noise
75%
Out-of-distribution Detection
68%
Noisy Labels
59%
Large Language Models
59%
Noisy Label Learning
48%
Federated Learning
45%
Learning with Noisy Labels
44%
Adversarial Training
40%
Transition Matrix
38%
Deep Neural Network
34%
Memorization
33%
Out-of-distribution Data
33%
Learning Methods
31%
Adversarial Robustness
29%
Semi-supervised Learning
25%
Adversarial Data
24%
Unlearning
24%
Unlabeled Data
24%
Sample Selection
23%
Training Data
23%
Deep Learning
21%
In-distribution
20%
Adversarial Examples
20%
Learning Framework
19%
Graph Neural Network
18%
Overfitting
18%
State-of-the-art Techniques
18%
Clean Label
18%
Vision-language Models
17%
Labeled Data
17%
Benchmark Dataset
17%
Trustworthy Machine Learning
16%
Out-of-distribution Generalization
16%
Publicly Available
16%
Few-shot
16%
Real-world Application
15%
Selection Strategy
15%
Noisy Data
15%
Class Label
14%
Foundation Models
14%
Early Stopping
14%
Adaptation
14%
Semi-supervised Method
13%
Robust Training
13%
Open World
13%
Popular
13%
Downstream Task
13%
Data Heterogeneity
13%
Outlier Exposure
13%
Machine Learning
13%
