Understanding Deep Learning Models with Visual Analytics (ML+VA)
Machine learning, especially deep learning with neural networks, has achieved unprecedented success in a variety of disciplines, such as object recognition with convolutional neural networks (CNN), speech recognition with recurrent neural networks (RNN), and image generation with generative adversarial networks (GAN). However, to date, there is no clear understanding on why these complicated neural networks perform so well, and how they might be improved. In GRAVITY lab, we resort to visual analytics approaches to fill the gap between the success of deep learning models and the deficiency in model interpretations. In collaboration with domain scientists, we develop integrated visual analytics systems to demonstrate model details, explore training dynamics in different levels with friendly user interactions, and propose potential solutions to improve the performance of machine learning models.
Publications:
Junpeng Wang, Liang Gou, Han-Wei Shen, Hao Yang : DQNViz: A Visual Analytics Approach to Understand Deep Q-Networks, IEEE transactions on visualization and computer graphics 25 (1), 288-298 (2019), [Best Paper Honorable Mention Award at IEEE VAST 2018]
Junpeng Wang, Liang Gou , Hao Yang, and Han-Wei Shen: GANViz: A Visual Analytics Approach to Understand the Adversarial Game, IEEE Transactions on Visualization and Computer Graphics, 24 (6), 1905-1917 (2018) [IEEE PacificVis 2018 Best Paper Award]
Junpeng Wang, Liang Gou, Wei Zhang, Hao Yang, Han-Wei Shen: DeepVID: Deep Visual Interpretation and Diagnosis for Image Classifiers via Knowledge Distillation, IEEE transactions on visualization and computer graphics 25 (6), 2168-2180 (2019)
Xiaonan Ji, Han-Wei Shen, Raghu Machiraju, Alan Ritter, and Po-Yin Yen: Visual Exploration of Neural Document Embedding in Information Retrieval: Semantics and Feature Selection, IEEE transactions on visualization and computer graphics 25 (6), 2181-2192 (2019).
Haoyu Li, Junpeng Wang, Yan Zheng, Liang Wang, Wei Zhang, and Han-Wei Shen: Compressing and Interpreting Word Embeddings with Latent Space Regularization and Interactive Semantics Probing, Information Visualization 2022
Ziwei Li, Jiayi Xu, Wei-Lun Chao, and Han-Wei Shen: Visual Analytics on Network Forgetting for Task-Incremental Learning. Computer Graphics Forum (Proc. EuroVis 2023).