News
Paper Alert!:
Is graph unlearning ready for practice? Read our ICLR 2026 paper for the answers!Delighted to have an oral presentation at NeurIPS 2025!:
How do you translate GNN predictions to logical rules explained in natural language? Through GnnXemplar!May, 2025: Hattrick @ KDD!
We will present three papers at KDD 2025 this year, all on machine learning for graphs.Can LLMs discover programs to solve graph edit distance?
Yes! We show how in our ICML work. This was a result of an amazing collaboration with Google DeepMind, Montreal by extending the FunSearch platform.Paper Alert!:
Graph condensation compresses massive graph datasets into tiny versions that train GNNs as effectively as the original. Read how we achieve this in our paper, which will appear at ICLR 2025.I hold the joint positions of Nick McKeown Chair Professor at the Department of Computer Science and Eng. and the Yardi School of AI at IIT Delhi. My research interests span the broad area of network science with particular focus on graph neural networks and spatio-temporal data analytics.
Internships: I am NOT offering any short-term projects. My apologies if I don't respond to your email.