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
Assistant Professor
,
Department of Computer Science
https://orcid.org/0000-0002-6338-0958
Email
bhanml
hkbu.edu
hk
Accepting PhD Students
2020
2025
Research activity per year
Overview
Fingerprint
Network
Projects / Grants
(10)
Research Output
(163)
Prizes / Awards
(8)
Activities
(7)
Similar Scholars
(6)
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
Keyphrases
Adversarial Attack
15%
Adversarial Data
38%
Adversarial Examples
20%
Adversarial Robustness
37%
Adversarial Training
68%
Benchmark Dataset
19%
Clean Label
22%
Data Heterogeneity
19%
Deep Learning
30%
Deep Network
19%
Deep Neural Network
48%
Distillation
21%
Distribution Shift
17%
Early Stopping
17%
Federated Learning
61%
Graph Convolutional Network
19%
Graph Neural Network
24%
In-distribution
18%
Invariant Features
15%
Label Noise
100%
Labeled Data
23%
Learning Methods
37%
Learning Paradigm
16%
Learning with Noisy Labels
62%
Machine Learning
16%
Maximum Mean Discrepancy
17%
Memorization
54%
Noisy Label Learning
67%
Noisy Labels
81%
Novel Class
15%
Open World
16%
Out-of-distribution Data
41%
Out-of-distribution Detection
80%
Out-of-distribution Generalization
27%
Outlier Exposure
15%
Overfitting
20%
Popular
21%
Real-world Application
17%
Robust Learning
15%
Robust Overfitting
15%
Sample Selection
37%
Selection Strategy
26%
Semi-supervised Learning
31%
Semi-supervised Method
18%
State-of-the-art Techniques
18%
Training Data
18%
Training Model
16%
Transition Matrix
47%
Unbiased Risk Estimation
18%
Unlabeled Data
37%
Computer Science
Adversarial Example
22%
Adversarial Machine Learning
87%
Annotation
29%
Approximation (Algorithm)
13%
Art Performance
18%
Bilevel Optimisation
19%
Capacity Model
15%
Class Distribution
22%
Classification Performance
20%
Clustering Graph
18%
Contrastive Learning
13%
Data Distribution
86%
Data Heterogeneity
19%
Decision Boundary
14%
Deep Learning Method
40%
Deep Neural Network
88%
Distributionally Robust Optimization
13%
Domain Adaptation
17%
Estimation Error
14%
Experimental Result
51%
Federated Learning
70%
Generalization Performance
16%
Gradient Descent
13%
Graph Convolution
19%
Graph Neural Network
30%
Independent Instance
13%
Language Modeling
15%
Large Language Model
19%
Learning Algorithm
25%
Learning Framework
20%
Learning System
53%
Machine Learning
53%
Network Parameter
13%
Problem Setting
14%
Regularization
14%
Representation Learning
18%
Risk Estimator
30%
Risk Minimization
19%
Sample Distribution
17%
Selection Process
21%
Self-Supervised Learning
15%
Semisupervised Learning
48%
Subgraphs
19%
Supervised Classification
19%
Supervised Learning
14%
Training Data
43%
Training Model
15%
Transition Matrix
61%
Unlabeled Data
37%
World Application
27%
