Konstantin Gubaev

Materials Chemistry · 2018–2020

A researcher in the Science corpus: 2 papers; trusts 11 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Materials Chemistry — 65 citations into it; #11,156 of 11,513 by trust here, #9,513 by citations
• Computational Theory and Mathematics — 25 citations into it
• Atomic and Molecular Physics, and Optics — 24 citations into it
• Computational Chemistry & Drug Discovery — 15 citations into it
• Physical and Theoretical Chemistry — 15 citations into it
• Biomedical Engineering — 5 citations into it

Whom Konstantin Gubaev trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. J. Behler
2. A. P. Bart'ok
3. Gábor Csányi
4. Alexander V. Shapeev
5. Evgeny V. Podryabinkin
6. S. Plimpton
7. Volker L. Deringer
8. Ralf Drautz
9. Justin S. Smith
10. Nongnuch Artrith

Who trusts Konstantin Gubaev overall

1. Ivan S. Novikov
2. Bohayra Mortazavi

Papers from Konstantin Gubaev's perspective

Ordered by how strongly the researchers Konstantin Gubaev trusts endorse each paper. Same corpus, a different order for every researcher.

1. Generalized neural-network representation of high-dimensional potential-energy surfaces.
2. Comparing molecules and solids across structural and alchemical space.
3. High-dimensional neural network potentials for metal surfaces: A prototype study for copper
4. Machine learning based interatomic potential for amorphous carbon
5. Neural Message Passing for Quantum Chemistry (International Conference on Machine Learning)
6. Fast and accurate modeling of molecular atomization energies with machine learning.
7. Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials
8. On representing chemical environments
9. Quantum-chemical insights from deep tensor neural networks
10. SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Their papers

• The MLIP package: moment tensor potentials with MPI and active learning (2020) — 643 citations
• Accelerating high-throughput searches for new alloys with active learning of interatomic potentials (2018) — 329 citations