Papers › Compositionally restricted attention-based network for materials property predictions

Compositionally restricted attention-based network for materials property predictions

28 May 2021archive 2025-07-28

Anthony Yu-Tung Wang, Steven K. Kauwe, Ryan J. Murdock, Taylor D. Sparks

In this paper, we demonstrate an application of the Transformer self-attention mechanism in the context of materials science. Our network, the Compositionally Restricted Attention-Based network (CrabNet), explores the area of structure-agnostic materials property predictions when only a chemical formula is provided. Our results show that CrabNet’s performance matches or exceeds current best-practice methods on nearly all of 28 total benchmark datasets. We also demonstrate how CrabNet’s architecture lends itself towards model interpretability by showing different visualization approaches that are made possible by its design. We feel confident that CrabNet and its attention-based framework will be of keen interest to future materials informatics researchers.

PaperPDFCode

Code

anthony-wang/CrabNet mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections