Search Results for author: Abhijit Gupta

Found 4 papers, 2 papers with code

D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion

1 code implementation30 Oct 2023 Jialin Chen, Shirley Wu, Abhijit Gupta, Rex Ying

The objective of GNN explainability is to discern the underlying graph structures that have the most significant impact on model predictions.

counterfactual Denoising +1

CardiGraphormer: Unveiling the Power of Self-Supervised Learning in Revolutionizing Drug Discovery

no code implementations3 Jul 2023 Abhijit Gupta

In the expansive realm of drug discovery, with approximately 15, 000 known drugs and only around 4, 200 approved, the combinatorial nature of the chemical space presents a formidable challenge.

Drug Discovery Self-Supervised Learning

ESPRIT: Explaining Solutions to Physical Reasoning Tasks

2 code implementations ACL 2020 Nazneen Fatema Rajani, Rui Zhang, Yi Chern Tan, Stephan Zheng, Jeremy Weiss, Aadit Vyas, Abhijit Gupta, Caiming Xiong, Richard Socher, Dragomir Radev

Our framework learns to generate explanations of how the physical simulation will causally evolve so that an agent or a human can easily reason about a solution using those interpretable descriptions.

Cannot find the paper you are looking for? You can Submit a new open access paper.