Le prochain séminaire du laboratoire CEDRIC aura lieu le vendredi 5 décembre à 14h, dans l’amphithéâtre Gaston Planté du CNAM (accès 35, 1er étage). Il sera organisé par l’équipe VERTIGO, et l’orateur sera Sandeep Kumar. Voici quelques informations concernant ce séminaire :
Title: Graph Coarsening: The Geometry of Abstraction in Scalable and Trustworthy Graph Learning.
Abstract: Graphs are the language of connected intelligence – capturing relationships across communication, biological, social, and financial systems. As these networks expand in scale, complexity, and sensitivity, learning over them calls for abstraction that is both principled and purposeful. This talk will highlight our group’s recent advances in graph coarsening, reimagining it as the mathematical foundation for scalable, interpretable, and privacy-conscious graph learning. By unifying spectral fidelity, feature alignment, and community preservation within a rigorous optimization framework, we develop algorithms that compress without compromise – retaining the essential geometry and semantics of the original graph while ensuring efficiency, trust, and theoretical soundness. Extending to dynamic, semi-supervised, and neural settings, these developments position graph coarsening as a geometry of abstraction – a bridge between structure and intelligence, and a cornerstone for the next generation of scalable, ethical, and adaptive graph machine learning.
Brief Profile: Dr. Sandeep Kumar is an Associate Professor in the Department of Electrical Engineering and the Yardi School of Artificial Intelligence at IIT Delhi, and leads the Machine Intelligence Signals and Networks (MISN) Lab. His work advances core algorithmic foundations while solving challenges in public health, equitable AI, finance, communication systems, and national security, supported through major government and industry collaborations. He is the Lead Investigator of Adi Vaani project, a flagship initiative of the Ministry of Tribal Affairs, developing multilingual AI technologies for low-resource tribal and regional languages to drive digital inclusion and cultural preservation. His broader vision centers on responsible and accessible AI that empowers communities and strengthens societal resilience. A dedicated educator and mentor, Dr. Kumar teaches core courses in Machine Learning and Optimization, and contributes actively to national AI capacity building through interdisciplinary collaborations, policy advisory efforts, and skill-development initiatives.