BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1770
DTSTAMP:20261006T090252Z
SUMMARY:Fully Differentiable Networks for Retrieval of Graph-Structured Obj
 ects
DESCRIPTION:Speaker: Abir De (IIT Bombay)\n\nAbstract: \nGiven a query grap
 h and a database of corpus graphs\, a graph retrieval system aims to deliv
 er the most relevant corpus graphs. Graph retrieval has a wide variety of 
 applications\, e.g.\, molecular fingerprint detection\, circuit design\, s
 oftware analysis\, and question answering. In such applications\, a corpus
  graph is relevant to a query graph\, if the query graph is (perfectly or 
 approximately) similar to the corpus graph. In this talk\, we will discuss
  a family of neural networks that can approximate similarity between graph
 s under different similarity notions. We consider graph retrieval based on
  subgraph matching. We discuss ISONET\, a novel interpretable neural edge 
 alignment formulation\, which can better learn the edge-consistent mapping
  necessary for subgraph matching. It incorporates a new scoring mechanism 
 that enforces an asymmetric relevance score tailored to subgraph matching.
  We also propose both late and early interaction neural formulations for t
 his task. Late interaction methods compute dense representations for the q
 uery and corpus graph separately\, and compare these representations using
  simple similarity functions at the last stage\, leading to highly scalabl
 e systems.  Early interaction methods combine information from both graph
 s right from the input stages\, and are usually considerably more accurate
 \, but slower. They are both based on a continuous relaxation of a node al
 ignment matrix between query and corpus nodes.Bio: Abir De is Bhide Family
  Chair Associate Professor at the Department of Computer Science and Engin
 eering in IIT Bombay. Before that\, he did his postdoctoral research  at 
 Max Planck Institute for Software Systems at Kaiserslautern\, Germany. He 
 received his PhD from Department of Computer Science and Engineering\, IIT
  Kharagpur. His PhD work was supported by Google India PhD Fellowship 2013
 .  Prior to this he did his BTech in Electrical Engineering and MTech in 
 Control Systems Engineering both from IIT Kharagpur. His research interest
 s are learning on structured objects with focus on graphs and sets.  He i
 s a recipient of Indian National Academy of Engineering Young Engineer Awa
 rd 2021 and Krithi Ramamritham Award for Creative Research 2020 at IIT Bom
 bay. He is the recipient of the 2026 Young Alumnus Achiever Award from IIT
  Kharagpur\n
URL:https://www.tcs.tifr.res.in/web/events/1770
DTSTART;TZID=Asia/Kolkata:20261008T160000
DTEND;TZID=Asia/Kolkata:20261008T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR