Gowthami Somepalli



I am a graduate student in Computer Science at the University of Maryland, College Park advised by Prof. Tom Goldstein. My broader research focus lies at the intersection of Machine Learning (ML) and Computer Vision with the aim of building practical ML systems that are interpretable and robust. My recent works range from developing novel deep learning architectures for diverse domains such as tables, images, and graphs, to building tools to explain and analyze the success/failure modes of common deep learning models. I am a recipient of the 2021 Kulkarni Fellowship.

Before starting my Ph.D., I worked in the industry for 8 years in various product and engineering roles and received my bachelor's from IIT Madras. My pivot to machine learning happened during my start-up years when I was building ML tools for fashion assistance. I’ve since been working towards building interpretable machine learning models with real-world applications.

I am always up for new collaborations, drop me an email if you want to chat!

Recent News

Research Highlights

Replication in diffusion models

We study why diffusion models copy and ways to mitigate the same. We found text conditioning plays a major role along with training data duplication. One way to mitigate is to use multiple captions per data point during training.

Replication in diffusion models

Understanding the training data replication in diffusion models. Examined DDPM models on Celeb-A and Oxford flowers and LAION-Aesthetics on Stable Diffusion v.1.4.

Decision Boundaries overview

Understanding the reproduciblity of various architectures from the decision boundary perspective. We also examine how the decision boundaries change as we increase the model capacity in the case of double-descent.

Gowthami Somepalli, Liam Fowl, Arpit Bansal, Ping Yeh-Chiang, Yehuda Dar, Richard Baraniuk , Micah Goldblum, Tom Goldstein.

SAINT overview

Improving predictions on structured tabular data using intersample attention and contrastive learning.

Gowthami Somepalli, Micah Goldblum, Avi Schwarzschild, C Bayan Bruss, Tom Goldstein.

PatchGame overview

Emergent communication via mid-level patches in a referential game played on a large-scale image dataset.

Kamal Gupta, Gowthami Somepalli, Anubhav Gupta, Vinoj Jayasundara, Matthias Zwicker, Abhinav Shrivastava

Adversarial Mirrored AE

We proposed mirrored wasserstein loss along with latent space regularization to recognize anomalies in case where there are no/ a few anomalies present during training time.

Gowthami Somepalli, Yexin Wu, Yogesh Balaji, Bhanukiran Vinzamuri, Soheil Feizi.

Adversarial Mirrored AE

In this work, we try to understand and predict which genes are important in any given tissue. We show that the gene expression is not the only important factor, but the location of the gene in PPI network also plays a role.

Gowthami Somepalli, Sarthak Sahoo, Arashdeep Singh, Sridhar Hannenhalli.

Adversarial Poisoning

In this paper, we desensitize networks to the effects of poisoning by creating poisons during training and injecting them into training batches.

Jonas Geiping, Liam Fowl, Gowthami Somepalli, Micah Goldblum, Michael Moeller, Tom Goldstein.