Fiza Husain

Hello, I am Fiza, trying to distill recent learnings into bite-sized insights.

I am a Research Fellow at Microsoft’s M365 Research Group where I am working on the Intelligent Monitoring problem. My work involves automating and optimizing monitor configurations to enhance system reliability, reducing missed detections and unnecessary alerts that typically rely on manual expertise. Currently, I’m delving into recommendation systems, exploring heterogeneous graph-based methods to incorporate multi-type user behavior and improve item predictions.

I graduated with a BTech in Computer Science and Engineering from International Institute of Information Technology, Hyderabad in 2022. During my time here, I worked as a research student with Prof. Praveen Paruchuri and Prof. Sujit Gujar on Privacy and Generalization in Deep Reinforcement Learning. Our work resulted in a novel Privacy-Aware Inverse Reinforcement Learning framework, published at AAAI’22.

My research interests lie at the intersection of Applied Machine Learning and Privacy-Preserving AI, where I explore ways to build models that respect data privacy while maintaining high performance. I am particularly drawn to Explainable AI and Graph Neural Networks, aiming to make complex neural architectures more interpretable and applicable to real-world scenarios. Through my work, I seek to bridge the gap between theoretical ML advances and practical applications while ensuring transparency and privacy in AI systems.

Aside from tech, I find joy in the arts. Drawing and painting in various mediums allows me to express my creative side, and you can find my latest creations on Twitter. I also absolutely love cats and mathematics!