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
Adversarial Example
27%
Adversarial Machine Learning
81%
Annotation
33%
Art Performance
17%
Bilevel Optimisation
18%
Capacity Model
14%
Class Distribution
20%
Classification Performance
19%
Clustering Graph
17%
Data Distribution
92%
Data Heterogeneity
19%
de-noising
15%
Decision Boundary
19%
Deep Learning Method
38%
Deep Neural Network
86%
Domain Adaptation
16%
Estimation Error
13%
Experimental Result
65%
Federated Learning
72%
Generalization Error
13%
Generalization Performance
15%
Graph Convolution
18%
Graph Neural Network
28%
Language Modeling
26%
Large Language Model
40%
Learning Algorithm
24%
Learning Framework
31%
Learning System
64%
Machine Learning
64%
Machine Learning Algorithm
15%
Negative Impact
13%
Optimization Problem
20%
Problem Setting
13%
Regularization
23%
Representation Learning
26%
Risk Estimator
28%
Risk Minimization
18%
Sample Distribution
16%
Selection Process
19%
Self-Supervised Learning
14%
Semisupervised Learning
45%
Subgraphs
18%
Supervised Classification
19%
Supervised Learning
13%
Training Data
47%
Training Dataset
15%
Training Model
15%
Transition Matrix
64%
Unlabeled Data
35%
World Application
32%
Keyphrases
Adversarial Attack
14%
Adversarial Data
36%
Adversarial Examples
21%
Adversarial Robustness
34%
Adversarial Training
64%
Benchmark Dataset
18%
Clean Label
21%
Data Heterogeneity
18%
Deep Learning
28%
Deep Network
18%
Deep Neural Network
45%
Distillation
19%
Distribution Shift
16%
Early Stopping
16%
Federated Learning
57%
Graph Convolutional Network
18%
Graph Neural Network
22%
In-distribution
17%
Invariant Features
14%
Label Noise
100%
Labeled Data
22%
Learning Methods
35%
Learning Paradigm
17%
Learning with Noisy Labels
58%
Machine Learning
15%
Maximum Mean Discrepancy
16%
Memorization
50%
Noisy Data
14%
Noisy Label Learning
63%
Noisy Labels
76%
Novel Class
14%
Open World
15%
Out-of-distribution Data
40%
Out-of-distribution Detection
75%
Out-of-distribution Generalization
25%
Outlier Exposure
14%
Overfitting
19%
Popular
20%
Real-world Application
16%
Robust Overfitting
14%
Sample Selection
35%
Selection Strategy
24%
Semi-supervised Learning
29%
Semi-supervised Method
17%
State-of-the-art Techniques
20%
Training Data
23%
Training Model
15%
Transition Matrix
44%
Unbiased Risk Estimation
17%
Unlabeled Data
35%
