Doctoral Thesis Proposal - Meng-Chieh (Jeremy) Lee

— 3:30pm

Location:
In Person and Virtual - ET - Reddy Conference Room, Gates Hillman 4405 and Zoom

Speaker:
MENG-CHIEH (JEREMY) LEE, Ph.D. Student, Computer Science Department, Carnegie Mellon University
https://mengchillee.github.io/

Explainable Mining of Graphs and Time Series: Algorithms and Applications

Given a social network, how can we predict the connections between users and determine whether they are based on shared hobbies or common friends? Similarly, how can we identify anomalies in time series data and explain why they are suspicious? Although recent machine learning models with improved performance are being developed, they are often black-box methods that are difficult to interpret. This leads us to explainable artificial intelligence (XAI), which offers valuable insights through its explanations.   

In this thesis proposal, we introduce carefully designed explainable methods tailored for graph and time series data, with diverse applications. Each method we proposed is either inherently explainable, or provides explanations for the data or decisions it makes.  

Thesis Committee 

Christos Faloutsos (Co-Chair)
Leman Akoglu (Co-Chair)
Geoffrey Gordon
Nina Mishra (Amazon)

Additional Information

In Person and Zoom Participation.  See announcement.

Event Website:
https://csd.cmu.edu/calendar/doctoral-thesis-proposal-mengchieh-jeremy-lee