See How Your Research Aligns
Create a free account to analyze your research alignment,
identify potential research gaps, and generate personalized
application documents for this professor.
Create Free Account
Mengdi Huai
Trustworthy Machine Learning
Explainable AI
Robust Machine Learning
Privacy-preserving Machine Learning
Fairness In Machine Learning
About
I am currently an assistant professor in the Department of Computer Science at Iowa State University. I obtained my Ph.D. in Computer Science from the University of Virginia, where I was supervised by Prof. Aidong Zhang. My research interests are in the general areas of machine learning and data mining, with a current focus on developing novel techniques to build trustworthy learning systems that are explainable, robust, private, and fair.
Research Performance Summary
2014-2025
Active Research Span
First Recorded Paper
Capture expression-dependent au relations for expression recognition
Year:
2014
Citations:
5
Venue:
2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)
Latest Recorded Paper
Towards Benchmarking Privacy Vulnerabilities in Selective Forgetting with Large Language Models
Year:
2025
Citations:
0
Venue:
arXiv preprint arXiv:2512.18035
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.
Publication Venues and Collaboration
Journal, Conference, and Book Publication Breakdown
Top Coauthors
Huai
Zhang
Wang
Research Impact by Period
Papers
10
Citations
84
Avg. Citations / Paper
8.4
H-Index
4
Papers
38
Citations
784
Avg. Citations / Paper
20.6
H-Index
15
Papers
15
Citations
1174
Avg. Citations / Paper
78.3
H-Index
13
Papers
1
Citations
5
Avg. Citations / Paper
5
H-Index
1
Contact and Professional Links
Detected Research Keywords
Patient Similarity Learning
Context Right Forgotten
Treatment Effect Estimation
Data Poisoning Attacks
Membership Inference Attacks
Understanding Enhancing Robustness
Individual Treatment Effect
Brain Effective Connectivity
Stable Explainable Attention
Rethinking Adversarial Robustness