You can sample nodes for scalable #GNN #training. But how do you do #scalable #inference?

In our latest paper (Oral #LogConference
) we introduce influence-based mini-batching (#IBMB) for both fast inference and training, achieving up to 130x and 17x speedups, respectively!

1/8 in 🧵

#Introduction

Hi all, I research the #robustness of #graph learning models doing a mix of #theory and #practice.

Currently, I am a PhD Student @ Technical University of Munich #TUM and a #relAI Fellow. You can find more information on my website: https://saper0.github.io/.

If you are interested in my work, always feel free to reach out :).

#introduction

I am a Ph.D. student in #MachineLearning. My research interests cover #uncertainty / #robustness in machine learning, #hierarchical / #causal inference, and #efficient machine learning :)

#introduction

Hi all!

I'm a research scientist joining #Google Research in a few weeks. I've written my PhD thesis at TU Munich, and interned at #DeepMind and #FAIR.

I've done research on #MachineLearning for graphs and molecules, but want to focus more on safety aspects in the future.

I am currently visiting #Berkeley, and will soon be based in #Zurich.