Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

Initial Structure to Relaxed Energy (IS2RE) | State-of-the-Art

graphs-1

Initial Structure to Relaxed Energy (IS2RE)

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in initial-structure-to-relaxed-energy-is2re-1

Trend

Dataset

Best Model

Actions

OC20

Libraries

Use these libraries to find initial-structure-to-relaxed-energy-is2re-1 models and implementations

Open-Catalyst-Project/ocp

2 papers 518

Datasets

OC20

Subtasks

No subtasks available.

Most implemented papers

Rotation Invariant Graph Neural Networks using Spin Convolutions

Zachary W. Ulissi, Anuroop Sriram, C. L. Zitnick, Aditya Grover, Abhishek Das, Muhammed Shuaibi, Adeesh Kolluru•Wed Jun 16 2021

A novel approach to modeling angular information between sets of neighboring atoms in a graph neural network is introduced and rotation invariance is achieved for the network's edge messages through the use of a per-edge local coordinate frame and a novel spin convolution over the remaining degree of freedom.

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Simple GNN Regularisation for 3D Molecular Property Prediction&Beyond

P. Battaglia, Petar Velivckovi'c, Alvaro Sanchez-Gonzalez, Jonathan Godwin, J. Kirkpatrick, Yulia Rubanova, Michael Schaarschmidt, Alex Gaunt•Mon Jun 14 2021

It is shown that simple noise regularisation can be an effective way to address GNN oversmoothing, and Noisy Nodes, a simple technique in which it is derived, can serve as a complementary building block in the GNN toolkit.

67 0

Paper Graph

GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets

Zachary W. Ulissi, Anuroop Sriram, C. L. Zitnick, Abhishek Das, Stephan Gunnemann, Muhammed Shuaibi, J. Gasteiger•Tue Apr 05 2022

The GemNet-OC model based on the large Open Catalyst 2020 (OC20) dataset is developed, which outperforms the previous state-of-the-art on OC20 by 16% while reducing training time by a factor of 10 and is substantially cheaper to train on.

91 0

Paper Graph

Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations

Anuroop Sriram, C. L. Zitnick, Abhishek Das, Siddharth Goyal, Brandon M. Wood•Thu Mar 17 2022

Graph Parallelism is introduced, a method to distribute input graphs across multiple GPUs, enabling us to train very large GNNs with hundreds of millions or billions of parameters.

37 0

Paper Graph

Adding a benchmark result helps the community track progress.