National Center for Supercomputing Applications WordPress Master Calendar

View Full Calendar

NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.

CS Compiler Seminar: TGLite: A Lightweight Programming Framework for Continuous-Time Temporal Graph Neural Networks

Event Type
Seminar/Symposium
Sponsor
CS Compilers Area
Location
Room 2406 (Siebel)
Date
Oct 28, 2024   4:30 - 5:30 pm  
Speaker
Wanyu Zhao
Views
11
Originating Calendar
Siebel School Speakers Calendar

CS Compiler Seminar: Please join us on 10/28/2024, from 4:30-5:30pm in the Room 2406 (Siebel) where Wanyu Zhao will give a talk, “TGLite: A Lightweight Programming Framework for Continuous-Time Temporal Graph Neural Networks”.  Please see their abstract below:

Speaker(s): Wanyu Zhao

Title: TGLite: A Lightweight Programming Framework for Continuous-Time Temporal Graph Neural Networks

Conference: ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS '24)

Author(s): Yufeng Wang (UIUC), Charith Mendis (UIUC)

Abstract: In recent years, Temporal Graph Neural Networks (TGNNs) have achieved great success in learning tasks for graphs that change over time. These dynamic/temporal graphs repre- sent topology changes as either discrete static graph snap- shots (called DTDGs), or a continuous stream of timestamped edges (called CTDGs). Because continuous-time graphs have richer time information, it will be crucial to have abstractions for programming CTDG-based models so that practitioners can easily explore new designs and optimizations in this space. A few recent frameworks have been proposed for pro- gramming and accelerating TGNN models, but these either do not support continuous-time graphs, lack easy compos- ability, and/or do not facilitate CTDG-specific optimizations.

 

link for robots only