Explainable AI + VIS

Human-Centered AI with the Power of Visualization


With the recent advances in machine learning, especially deep learning, we have witnessed increasing applications of AI in various domains. The past few years have seen a growing interest towards more explainable machine learning systems.

At HKUST VisLab, we focus on human-centered approaches to make AI explainable, interactive, and trusworthy. In critical domains such as finance, security, and healthcare, explanability allows us to make more reliable decisions powered by the collaboration of machine- and human-intelligence. Interactivity makes the exploration, creation, and customization of AI at ease. With XAI, it is easier to build trustworthy AI solutions: we trust its performance, know when and where it is possible to fail, and can decide whether the AI solution meets our needs.


ProtoSteer: Steering Deep Sequence Model with Prototypes

Yao Ming, Panpan Xu, Furui Cheng, Huamin Qu, Liu Ren
IEEE Transactions on Visualization and Computer Graphics, 2019 (accepted).

Visual Genealogy of Deep Neural Networks

Qianwen Wang, Jun Yuan, Shuxin Chen, Su Hang, Huamin Qu, Shixia Liu
IEEE Transactions on Visualization and Computer Graphics, 2019 (accepted).

Interpretable and Steerable Sequence Learning via Prototypes

Yao Ming, Panpan Xu, Huamin Qu, Liu Ren
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019 (Oral Presentation).

ATMSeer: Increasing Transparency and Controllability in Automated Machine Learning

Qianwen Wang, Yao Ming, Zhihua Jin, Qiaomu Shen, Dongyu Liu, Micah J. Smith, Kalyan Veeramachaneni, Huamin Qu
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2019.

RuleMatrix: Visualizing and Understanding Classifiers with Rules

Yao Ming, Huamin Qu, Enrico Bertini
IEEE Transactions on Visualization and Computer Graphics, 2019.

DeepTracker: Visualizing the Training Process of Convolutional Neural Networks

Dongyu Liu, Weiwei Cui, Kai Jin, Yuxiao Guo, Huamin Qu
ACM Transactions on Intelligent Systems and Technology, 2018.

iForest: Interpreting Random Forests via Visual Analytics

Xun Zhao, Yanhong Wu, Dik Lun Lee, Weiwei Cui
IEEE Transactions on Visualization and Computer Graphics, 2019.

EmbeddingVis: A Visual Analytics Approach to Comparative Network Embedding Inspection

Quan Li, Kristanto Sean N, Hammad Haleem, Qiaoan Chen, Chris Yi, Xiaojuan Ma
Proceedings of IEEE Visual Analytics Science and Technology 2018, Berlin, Germany, 2019.

A Survey on Visualization for Explainable Classifier

Yao Ming, Huamin Qu
Unpublished Manuscript (PQE Report), 2017.

Understanding Hidden Memories of Recurrent Neural Networks (Yelp Data Challenge Grand Prize Winnner)

Yao Ming, Shaozu Cao, Ruixiang Zhang, Zhen Li, Yuanzhe Chen, Yangqiu Song, Huamin Qu
Proceedings of IEEE Visual Analytics Science and Technology 2017, 2017.

CNNComparator: Comparative Analytics of Convolutional Neural Networks

Haipeng Zeng, Hammad Haleem, Xavier Plantaz, Nan Cao, Huamin Qu
VADL 2017: Workshop on Visual Analytics for Deep Learning, 2017.

Towards Better Understadning of Deep Learning with Visualization

Haipeng Zeng, Huamin Qu
Unpublished Manuscript (PQE Report), 2016.

The Team

Huamin Qu


Yao Ming

Ph.D. Candidate

Dongyu Liu

Ph.D. Candidate

Qianwen Wang

Ph.D. Candidate

Haipeng Zeng

Ph.D. Candidate

Furui Cheng

Ph.D. Student

Qiaomu Shen

Ph.D. Candidate


Xun Zhao

Ph.D. Candidate

Quan Li

Ph.D. Candidate



CYT 3007, Hong Kong University of Science and Technology
Clear Water Bay, Kowloon, Hong Kong


Yao Ming: ymingaa at ust dot hk