Skip to main navigation
Skip to search
Skip to main content
Hong Kong Baptist University Home
Help & FAQ
Home
Scholars
Departments / Units
Research Output
Projects / Grants
Prizes / Awards
Activities
Press/Media
Student theses
Datasets
Search by expertise, name or affiliation
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
2020
2026
Research activity per year
Overview
Fingerprint
Network
Projects / Grants
(13)
Research Output
(190)
Prizes / Awards
(8)
Activities
(7)
Similar Scholars
(6)
Supervised Work
(2)
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
Data Distribution
92%
Deep Neural Network
86%
Adversarial Machine Learning
81%
Federated Learning
72%
Experimental Result
65%
Learning System
64%
Transition Matrix
64%
Machine Learning
64%
Training Data
47%
Semisupervised Learning
45%
Large Language Model
40%
Deep Learning Method
38%
Unlabeled Data
35%
Annotation
33%
World Application
32%
Learning Framework
31%
Risk Estimator
28%
Graph Neural Network
28%
Adversarial Example
27%
Language Modeling
26%
Representation Learning
26%
Learning Algorithm
24%
Regularization
23%
Class Distribution
20%
Optimization Problem
20%
Data Heterogeneity
19%
Selection Process
19%
Classification Performance
19%
Decision Boundary
19%
Supervised Classification
19%
Risk Minimization
18%
Subgraphs
18%
Bilevel Optimisation
18%
Graph Convolution
18%
Art Performance
17%
Clustering Graph
17%
Sample Distribution
16%
Domain Adaptation
16%
de-noising
15%
Generalization Performance
15%
Machine Learning Algorithm
15%
Training Dataset
15%
Training Model
15%
Self-Supervised Learning
14%
Capacity Model
14%
Problem Setting
13%
Negative Impact
13%
Estimation Error
13%
Generalization Error
13%
Supervised Learning
13%
Keyphrases
Label Noise
100%
Noisy Labels
76%
Out-of-distribution Detection
75%
Adversarial Training
64%
Noisy Label Learning
63%
Learning with Noisy Labels
58%
Federated Learning
57%
Memorization
50%
Deep Neural Network
45%
Transition Matrix
44%
Out-of-distribution Data
40%
Adversarial Data
36%
Learning Methods
35%
Sample Selection
35%
Unlabeled Data
35%
Adversarial Robustness
34%
Semi-supervised Learning
29%
Deep Learning
28%
Out-of-distribution Generalization
25%
Selection Strategy
24%
Training Data
23%
Graph Neural Network
22%
Labeled Data
22%
Clean Label
21%
Adversarial Examples
21%
State-of-the-art Techniques
20%
Popular
20%
Distillation
19%
Overfitting
19%
Benchmark Dataset
18%
Deep Network
18%
Graph Convolutional Network
18%
Data Heterogeneity
18%
Unbiased Risk Estimation
17%
In-distribution
17%
Semi-supervised Method
17%
Learning Paradigm
17%
Real-world Application
16%
Early Stopping
16%
Maximum Mean Discrepancy
16%
Distribution Shift
16%
Training Model
15%
Open World
15%
Machine Learning
15%
Noisy Data
14%
Adversarial Attack
14%
Invariant Features
14%
Novel Class
14%
Robust Overfitting
14%
Outlier Exposure
14%
