My name is Adarsh Jamadandi. I have a Master’s degree in Computer Science from Saarland University. My research interests include Graph Representation Learning and Geometric Deep Learning.

I am actively looking for PhD positions. Please feel free to reach out to me if you have any interesting opportunities!

I finished my master’s thesis at the Relational Machine Learning Lab under the supervision of Dr. Rebekka Burkholz.

Previously, I completed my Bachelors in Electronics and Communication Engineering with Dr. Uma Mudenagudi as my advisor.

My CV can be found here.

Updates

September , 2024 Accepted at NeurIPS 2024! Spectral Graph Pruning Against Over-Squashing and Over-Smoothing. We introduce the Braess Paradox for the first time in context of GNNs. We propose a novel graph pruning strategy that can mitigate both over-squashing and over-smoothing and bonus also find graph lottery tickets!
August, 2024 My master's thesis is now online! On the Importance of Graph-Task Alignment for Graph Neural Networks.
May, 2024 New Pre-print Alert! SoLAR : Surrogate Label Aware Rewiring for Graph-Task Alignment. Given a graph and a chosen downstream task such as node classification, what are the factors that determine if a GNN can solve the task? We propose graph-task alignment as one of the main factors. We also propose a novel graph rewiring strategy that can induce such alignment to improve GNN performance!
November, 2022 Started as a research assistant at the Relational Machine Learning Group, CISPA, under Prof. Dr. Rebekka Burkholz. I will be working on improving the generalizability of graph neural networks by trying to tackle 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.
November, 2020 Probabilistic Word Embeddings in Kinematic Space, accepted at ICPR, 2020!