Hi 👋

I’m Adarsh Jamadandi. I’m a PhD student at IRISA, Rennes, working on Graph Representation Learning and Geometric Deep Learning under the supervision of Dr. Nicolas Keriven and co-supervised by Dr. Aline Roumy.

I completed my Master’s in Computer Science at Saarland University, Germany, where I wrote my thesis at the Relational Machine Learning Lab with Dr. Rebekka Burkholz.

Before starting my PhD, I worked as a research assistant at the SprintML Lab with Franziska Boenisch and Adam Dziedzic.

I hold a Bachelor’s degree in Electronics and Communication Engineering from India. My thesis was on anomaly detection in videos with Dr. Uma Mudenagudi as my advisor.

Updates

September 2025 Excited! to start as a PhD student at IRISA, Rennes.

May 2025 Now pre-print alert! Memorization in Graph Neural Networks.

March 2025 Started as a research assistant at SprintML Lab under the supervision of Franziska Boenisch and Adam Dziedzic. I will be working on understanding if GNNs also memorize.

January 2025 Now accepted at ICLR 2025! GNNs Getting ComFy: Community and Feature Similarity Guided Rewiring .

September 2024 Accepted at NeurIPS 2024! Spectral Graph Pruning Against Over-Squashing and Over-Smoothing.

August 2024 My master's thesis is now online! On the Importance of Graph-Task Alignment for Graph Neural Networks.

November 2022 Started as a research assistant at the Relational Machine Learning Group, under Dr. Rebekka Burkholz. I will be working on improving the generalizability of GNNs by tackling problems like over-squashing and over-smoothing.

December 2020 Graph of Thrones: Adversarial Perturbations dismantle Aristocracy in Graphs is accepted at AAAI'2021 Student Poster Program, and the extended version is accepted at DiffGeo4DL, NeurIPS 2020.