ML Research | Srinitish Srinivasan

About Me

I am a final-year undergraduate student in Computer Science at Vellore Institute of Technology, specializing in representation learning, particularly on graph-based models, out-of-distribution (OOD) generalization, and adversarial robustness. Beginning May, I will be joining Indian Institute of Technology,Delhi as a Research Fellow under the supervision of Dr. Tanmoy Chakraborty.

My final-year research focuses on developing Graph Isomorphic Networks for Riemannian manifolds, exploring their theoretical foundations and practical implications. Previously, I was a visiting research student at the University of Lincoln, where I worked on mitigating spurious correlations in YOLO object detection models under the guidance of Dr. Karthik Seemakurthy.

Representation Learning

OOD Generalization

Graph Machine Learning

Download CV

Recent Publications

Lorentzian Graph Isomorphic Network

Srinitish Srinivasan, Omkumar CU. Preprint

We propose a novel graph neural network for Riemannian manifolds and has a discriminative power as poweful as the WL test for non-isomorphic graphs.

Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation

Jaskaran Singh Walia, Aarush Sinha, Srinitish Srinivasan, Srihari Unnikrishnan. Preprint

Designed a CausalGAN and RL-based framework to generate synthetic bond yield data for enhanced forecasting. Integrated a fine-tuned LLM to provide trading signals, risk assessments, and volatility projections.

Leveraging Joint Predictive Embedding and Bayesian Inference in Graph Self Supervised Learning

Srinitish Srinivasan, Omkumar CU. Preprint

A novel, scalable graph self supervised technique that leverages both joint predictive embedding architecture and Bayesian inference.

Detecting Side Effects of Adverse Drug Reactions using Graph Self Supervised Learning

Omkumar CU, Srinitish Srinivasan, Varenya Pathak. IEEE Access

Developed a Graph Neural Network framework to predict adverse drug reactions from drug-drug interactions. Our approach enhances early detection of side effects, addressing a major challenge in pharmacovigilance.

View All Publications

Get In Touch

Contact Information

I'm always interested in discussing research collaborations, speaking opportunities, freelancing opportunities, or just chatting about AI/ML. Feel free to reach out!

smudge0110@icloud.com

Discord

smudge0110

Office

LLCS2, Yardi School of AI, IIT Delhi

Hi, I'm Srinitish Srinivasan