Professor at IIT-Delhi
📌 Mohit Kataria is a 4th-year Ph.D. scholar at the School of Artificial Intelligence, IIT Delhi, India, specializing in Graph Machine Learning. His research focuses on scalability of graph algorithms, including graph coarsening, structure learning, federated learning, and large-scale applications. He has published in top venues like NeurIPS, MICAAI, and CBME. Mohit holds a Master’s in Computer Applications (80.1%) and has expertise in Python, PyTorch, TensorFlow, CUDA, and C/C++. His skill set spans deep learning (GNNs, CNNs, RNNs), machine learning (SVM, XGBoost), and mathematical optimization.
Publication Profile
Google Scholar
Academic Background 🎓🔬
📌 Mohit Kataria is a Ph.D. scholar in Graph Machine Learning at the MISN Lab, IIT Delhi, maintaining an 8.0 CGPA since August 2021. He holds a Master’s in Computer Applications (80.1%) from May 2020. His technical expertise spans Python, PyTorch, TensorFlow, CUDA, MPI, C/C++, Java, MySQL, and Erlang. 🖥️ He specializes in Machine Learning (SVM, Random Forest, XGBoost, Decision Trees) and Deep Learning (ANNs, GNNs, CNNs, RNNs, LSTM, VAE, GANs). 📊 His strong foundation in Linear Algebra, Probability, and Optimization fuels his research in scalable graph algorithms and AI applications. 🚀
💼 Professional Experience of Mohit Kataria
📌 Mohit Kataria has been actively involved in AI/ML training at IIT Delhi (2021-Present), where he has helped train 260+ industry experts in a six-month AI/ML program, covering fundamentals to advanced ML models. 🎓 He also conducted 5-day ML training programs for CAG and CRIS, Government of India. As a WebMaster (2022-Present), he manages the Yardi-ScAI and MISN group websites. 🌐 Previously, as a Member of Technical Staff at Octro.Inc (2020-2021), he led a team of four and contributed to the backend architecture of multiplayer games like Poker3D and Soccer Battles. 🎮🚀
🔬 Research Focus of Mohit Kataria
📌 Mohit Kataria specializes in Graph Machine Learning, focusing on graph coarsening, structure learning, and scalable AI applications. His work enhances GNN performance on heterophilic datasets 🧠, improves large-scale single-cell data analysis 🧬, and optimizes histopathological image processing 🔍. His research, published in NeurIPS, MICAAI, and CBME, develops efficient graph-based frameworks for biomedical and computational applications. 🏥 His expertise spans AI-driven healthcare, graph-based AI models, and machine learning scalability, making significant contributions to bioinformatics, medical imaging, and large-scale data processing. 🚀
Publication Top Notes