- Academics
-
Research
-
Centres
- E-Health Research Centre (EHRC)
- Machine Intelligence & Robotics CoE (MINRO)
- Centre for IT & Public Policy (CITAPP)
- Cognitive Computing CoE (CCC)
- Centre for Accessibility in the Global South (CAGS)
- COMET Tech Innovation Hub (NM-ICPS)
- IIITB Innovation Centre
- Modular Open-Source Identity Platform (MOSIP)
- Centre for Open Societal Systems (COSS)
- Centre for Digital Public Infrastructure | CDPI
-
Labs
- Surgical and Assistive Robotics Lab
- Scalable Data Science and AI Lab
- Graphics-Visualization-Computing-Lab
- Web Science Lab
- Multimodal Perception Lab
- Software Engineering Lab
- High Density Electronic Systems Lab
- Networking and Communication Lab
- Remote Sensing, GIS and Spatial Computing Lab
- Indian Knowledge System (IKS) Lab
- Smart City Lab
- Ascend Studio
- Radar Sensing Lab
- CSSMP
- Advanced Wireless Communications Lab
- Speech Lab
- Connected Devices and Wearables Lab
- Outreach
- Publications
- Policy
-
Centres
- Placements
- Campus Life
- Media
- People
- About Us
Assistant Professor
Education : Ph.D. (IISc Bangalore)
Naganand Yadati holds a PhD in Computer Science from the Indian Institute of Science, awarded in 2021. He specialises in machine learning and deep learning with expertise in graph neural networks and hypergraphs. His PhD focused on novel extensions of graph neural networks to hypergraphs. Before joining IIIT-Bangalore, he was a postdoctoral researcher at the National University of Singapore, where he focused on simplified models for graph learning. His research has resulted in multiple publications at premier venues, including NeurIPS, ICDM, and TMLR.
Graph Neural Networks, Deep Learning, Foundation Models, Machine Learning
1. LocalFormer: Mitigating Over-Globalising in Transformers on Graphs with Localised Training, In Transactions of Machine Learning Research (TMLR) 2025
2. HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs, In Neural Information Processing Systems (NeurIPS) 2019
3. Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs, In Neural Information Processing Systems (NeurIPS) 2020
1. Introduction to Optimization, August - Decemeber 2025
2. Deep Learning and Foundation Models, August - December 2025
1. Top Reviewer for Learning on Graphs Conference 2024
2. Outstanding Reviewer for International Conference on Machine Learning 2022
3. Top 10% Reviewer for Neural Information Processing Systems 2020
4. Google Travel Grant for Neural Information Processing Systems 2019