Search Results for author: Ameya Daigavane

Found 5 papers, 4 papers with code

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for Molecule Generation

1 code implementation27 Nov 2023 Ameya Daigavane, Song Kim, Mario Geiger, Tess Smidt

We present Symphony, an $E(3)$-equivariant autoregressive generative model for 3D molecular geometries that iteratively builds a molecule from molecular fragments.

Learning Integrable Dynamics with Action-Angle Networks

1 code implementation24 Nov 2022 Ameya Daigavane, Arthur Kosmala, Miles Cranmer, Tess Smidt, Shirley Ho

Here, we propose an alternative construction for learned physical simulators that are inspired by the concept of action-angle coordinates from classical mechanics for describing integrable systems.

Numerical Integration

Node-Level Differentially Private Graph Neural Networks

1 code implementation23 Nov 2021 Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain

Graph Neural Networks (GNNs) are a popular technique for modelling graph-structured data and computing node-level representations via aggregation of information from the neighborhood of each node.

Privacy Preserving

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