Amit Roy
Graduate Student
Graduate Teaching Assistant
Joined department: Fall 2022
Education
Amit Roy is a graduate student in Purdue Computer Science and joined the department after being offered a Ross Fellowship. His research focus is
- Graph Machine Learning
- Large Language Models
- Data Mining
Until 2023,Amit worked on a project with Prof. Pan Li on Graph Anomaly Detection (GAD) and developed deep learning architectures using neighborhood reconstruction-based graph autoencoder and energy-based models funded by Sony, Belgium.
Before joining Purdue Computer Science in the Fall of 2022, he worked as a research assistant in the Artificial Intelligence and Cybernetics Lab (AGenCy Lab) at Independent University Bangladesh where he worked on several research projects related to deep learning on graphs, funded by the ICT Division Government of Bangladesh. Also, he has experience working as a software engineer at Tiger IT Bangladesh Limited where his responsibility was to work on the back-end part of applied computer vision projects from real-time video data e.g. automated number plate recognition and object detection.
Earlier in 2020, he finished his undergrad at the Department of Computer Science, University of Dhaka, Bangladesh, securing the first position in the Faculty of Engineering and Technology with a CGPA of 3.96 on a scale of 4.00.
Academic Activities @ Purdue CS:
Spring 2024*:
Teaching Assistant
CS 37300: Machine Learning and Data Mining
Instructor: Prof. Steve Hanneke and Prof. Ruqi Zhang
Fall 2023:
CS 58000 Algorithm Design, Analysis, And Implementation
CS 57300: Data Mining
CS 54100: Database Systems
Teaching Assistant
CS 57800: Statistical Machine Learning
Instructor: Prof. Ruqi Zhang
Spring 2023:
CS 58700: Foundations Of Deep Learning
(CS 69000-DPL: Deep Learning)
CS 57800: Statistical Machine Learning
CS 57700: Natural Language Processing
Fall 2022:
CS 59300-CLG: Computation and Learning over Graphs
CS 53600: Data Communication And Computer Network
Selected Publications
- GAD-EBM: Graph Anomaly Detection using Energy-Based Models
New Frontiers in Graph Learning (GLFRONTIERS), NeurIPS Workshop 2023
Amit Roy, Juan Shu, Olivier Elshocht, Jeroen Smeets, Ruqi Zhang, Pan Li [Paper]