Sandeep Kumar is an assistant professor in the Department of Electrical Engineering and School of Artificial Intelligence (ScAI)  at the Indian Institute of Technology Delhi (IIT Delhi). He heads the Machine Intelligence Signals and Networks (MISN) lab at IIT Delhi. His current research focuses on graphical models, manifolds, semi-supervised learning, and large-scale optimization. He received his M.Tech and Ph.D. degrees from the Indian Institute of Technology (IIT), Kanpur, and completed his postdoc from the Hong Kong University of Science and Technology.

Research: I supervise the Machine Intelligence Signals and Networks (MISN) Lab at IIT Delhi. The overarching theme of our research efforts lies in the coherent interaction between optimization, machine learning, signal processing, and graphical models.  Specific problems of interest include:

• Graph Compression

• Machine Learning over non-Euclidean Spaces

• Fair Federated Personalized Graph Neural Networks

• Applications of Graph ML in Earth science, Neuroscience, Wireless communication, and Circuit Design

• Our Paper "A Novel Coarsened Graph Learning Method for Scalable Single-Cell Data Analysis" Accepted tp Computers and Biology Journal, Congrats to Mohuit and Ekta.

• Our Paper "HyperDefender: A Robust Framework for Hyperbolic GNNs", was accepted to AAAI 2025, Congrats to Nikita! 

• Our paper "𝐀 𝐔𝐧𝐢𝐟𝐢𝐞𝐝 𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐚𝐭𝐢𝐨𝐧-𝐁𝐚𝐬𝐞𝐝 𝐅𝐫𝐚𝐦𝐞𝐰𝐨𝐫𝐤 𝐟𝐨𝐫 𝐂𝐞𝐫𝐭𝐢𝐟𝐢𝐚𝐛𝐥𝐲 𝐑𝐨𝐛𝐮𝐬𝐭 𝐚𝐧𝐝 𝐅𝐚𝐢𝐫 𝐆𝐫𝐚𝐩𝐡 𝐍𝐞𝐮𝐫𝐚𝐥 𝐍𝐞𝐭𝐰𝐨𝐫𝐤𝐬", accepted to IEEE Transactions on Signal Processing, Congrats to Vipul and Avadesh!

• Our paper "𝐂𝐨𝐑𝐄-𝐁𝐎𝐋𝐃: 𝐂𝐫𝐨𝐬𝐬-𝐃𝐨𝐦𝐚𝐢𝐧 𝐑𝐨𝐛𝐮𝐬𝐭 𝐚𝐧𝐝 𝐄𝐪𝐮𝐢𝐭𝐚𝐛𝐥𝐞 𝐄𝐧𝐬𝐞𝐦𝐛𝐥𝐞 𝐟𝐨𝐫 𝐁𝐎𝐋𝐃 𝐒𝐢𝐠𝐧𝐚𝐥 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬", accepted to Machine Learning for Health Symposium, ML4H proceedings track. Congratulations to Jyotimsita and Vipul!

• Our Paper " UGC: Universal Graph Coarsening" got accepted to the NeurIPS 2024 main track. Congratulations Mohit!

• Our paper "Optimization-based Framework for Semi-Supervised Attributed Graph Coarsening" got accepted to UAI 2024. Congratulations to Manoj, Subhanu, and Archit!

• Our paper, "No Prejudice! Fair Federated Graph Neural Networks for Personalized Recommendation, "was accepted to AAAI 2024. Congratulations to Nimesh and Anuj for their great efforts!

• Our paper, " Linear Complexity Framework for Feature-Aware Graph Coarsening via Hashing," was accepted to the NeurIPS Workshop in Frontiers in Graph Learning. Congratulations to Moohit, Aditi, and Rocktim. 

• Congratulations to Hemanthika and Subhanu for receiving the prestigious PMRF doctoral fellowship