Can we learn temporal models even with some missing observations? We offer an efficient neural point process named IMTPP in this paper, which can accurately predict next events in a temporal event stream.
I am an associate professor and the DS Chair of Artificial Intelligence at the Department of Computer Science and Engineering at IIT Delhi. Until recently I worked as a research scientist at IBM Research as part of their AI Research team. Before joining IBM in 2014, I worked as a faculty member at IIIT Delhi, where I founded the Max-Planck Partner Group on Large-scale Graph Search and Mining. Even before joining IIIT-D, I was a senior researcher at the Max-Planck Institute for Informatics (MPII) as part of the Databases and Informatics Systems department. My PhD (2005) was from the Indian Institute of Science, Bangalore.
PhD, 1998-2005
IISc
BE, 1991-1995
Bangalore University
I am NOT offering any short-term projects for internships and I do not have the bandwidth to respond to requests about summer or winter internships. If you are interested in working with me, I recommend you apply for a short-term employment in one of my projects, or join the B.Tech./M.Tech./Ph.D. programs in IIT-Delhi.
Please make an appointment based on my availability below
Working Hours: 9:30AM - 12:30PM; 2:00PM - 5:30PM
Understand and implement large-scale text search systems effectively and efficiently
Datastructures and algorithms using Java.
Focus on Information Retrieval
Focus on Knowledge Graph Management and IR
Focus on Information Retrieval
Can we learn temporal models even with some missing observations? We offer an efficient neural point process named IMTPP in this paper, which can accurately predict next events in a temporal event stream.
Great start to 2021 – honored to be appointed the “DS Chair Professor of Artificial Intelligence”!
Our SIGMOD 2019 work on regular simple path queries on billion-node graphs with zero indexing receives SIGMOD reproducibility badge!
Woot!!! Our paper proposing a novel language modeling approach for temporal information needs was awarded the Test of Time award at ECIR 2020!
Building Platforms for Privacy-preserving and Aggregated Analysis of Media