SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

By Kristof T. Schütt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, K. Müller. 2017

1,449 citations recorded by the source corpus.

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms in molecules are not restricted to a grid. Instead, their precise locations contain essential physical information, that would get lost if discretized. Thus, we propose to use continuous-filter convolutional layers to be able to model local correlations without requiring the data to lie on a grid. We apply those layers in SchNet: a novel deep learning architecture modeling quantum interactions in molecules. We obtain a joint model for the total energy and interatomic forces that follows fundamental quantum-chemical principles. This includes rotationally invariant energy predictions and a smooth, differentiable potential energy surface. Our architecture achieves state-of-the-art performance for benchmarks of equilibrium molecules and molecular dynamics trajectories. Finally, we introduce a more challenging benchmark with chemical and structural variations that suggests the path for further work.

Subfields: Artificial Intelligence, Materials Chemistry, Physical and Theoretical Chemistry, Model Architectures, AI for Physical Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Yoshua Bengio
  2. Jianfeng Gao
  3. Percy Liang
  4. Mohit Bansal
  5. Jure Leskovec
  6. Dacheng Tao
  7. Quoc V. Le
  8. William L. Hamilton

In Materials Chemistry

  1. Tess E. Smidt
  2. Tommi S. Jaakkola
  3. Regina Barzilay
  4. Jian Tang
  5. Shitong Luo
  6. Frank No'e
  7. K. Müller
  8. Max Welling

In Physical and Theoretical Chemistry

  1. Tess E. Smidt
  2. Tommi S. Jaakkola
  3. Risi Kondor
  4. Regina Barzilay
  5. Shitong Luo
  6. Jian Tang
  7. Evgeny V. Podryabinkin
  8. Wengong Jin

In Model Architectures

  1. Tess E. Smidt
  2. Tommi S. Jaakkola
  3. Max Welling
  4. Regina Barzilay
  5. Erik J. Bekkers
  6. Risi Kondor
  7. Daniel E. Worrall
  8. Mario Geiger

In AI for Physical Sciences

  1. Risi Kondor
  2. Frank No'e
  3. Tess E. Smidt
  4. K. Müller
  5. Grgoire Montavon
  6. Shitong Luo
  7. Stephan Günnemann
  8. Johannes Klicpera

Citations in the corpus