Visual Analytics for Human-Centered Artificial Intelligence

PhD Thesis Proposal Defence


Title: "Visual Analytics for Human-Centered Artificial Intelligence"

by

Mr. Furui CHENG


Abstract:

The recent advance in Artificial Intelligence (AI) technologies offers 
exciting opportunities to solve challenging problems with data-driven 
methods. However, when bringing these technologies from the laboratory to 
people's lives, challenges arise from both technical and ethical 
perspectives. When tackling these issues, a principle is that humans 
should be put into the center position, i.e., AI empowers and enhances 
people. Towards this direction, we made visual analytics approaches in 
response to three progressive, vital questions.


(1) How to provide transparency to ML models?

We formulated this problem as probing and explaining the model's decision 
boundaries. We explored using counterfactuals (i.e., how to alter a model 
prediction with minimal changes to the data input) to provide truthful and 
human-friendly explanations. We further developed DECE, a visual analytics 
system that helps users mentally approximate the model's decision 
boundaries by iteratively proposing and refining hypotheses.


(2) How to inform users' decision-making with explainable ML?

We targeted clinical scenarios and conducted an interview study with the 
six clinicians to understand the challenges in adopting ML predictions and 
explanations in clinical decision-making. Following an iterative design 
process, we further designed, developed, and evaluated VBridge, a visual 
analytics tool that seamlessly incorporates ML explanations into 
clinicians' decision-making workflow.


(3) How to incorporate users' knowledge into ML models?

We worked with seven molecular biologists to identify the challenges and 
expectations in applying automatic single-cell annotation tools, which 
transfer labels from reference datasets (e.g., single-cell atlases) to 
newly produced data. We further proposed Polyphony, a visual analytics 
system extended from an existing transfer-learning method that supports 
biologists in incorporating their knowledge into the ML model.


This thesis contributes to the fields of visualization, human-computer 
interaction (HCI), and machine learning with novel interactive analytics 
techniques, design lessons and implications, and open-source software. A 
list of underexplored directions was further derived from these studies to 
inspire future research in human-centered AI.


Date:			Wednesday, 1 June 2022

Time:                  	2:00pm - 4:00pm

Zoom Meeting: 		https://hkust.zoom.us/j/2816986601

Committee Members:	Prof. Huamin Qu (Supervisor)
  			Prof. Ke Yi (Chairperson)
 			Dr. Hao Chen
 			Prof. Raymond Wong


**** ALL are Welcome ****