CrysMMNet: Multimodal Representation for Crystal Property Prediction

Kishalay Das, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee, Niloy Ganguly
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, PMLR 216:507-517, 2023.

Abstract

Machine Learning models have emerged as a powerful tool for fast and accurate prediction of different crystalline properties. Exiting state-of-the-art models rely on a single modality of crystal data i.e crystal graph structure, where they construct multi-graph by establishing edges between nearby atoms in 3D space and apply GNN to learn materials representation. Thereby, they encode local chemical semantics around the atoms successfully but fail to capture important global periodic structural information like space group number, crystal symmetry, rotational information etc, which influence different crystal properties. In this work, we leverage textual descriptions of materials to model global structural information into graph structure and learn a more robust and enriched representation of crystalline materials. To this effect, we first curate a textual dataset for crystalline material databases containing descriptions of each material. Further, we propose CrysMMNet, a simple multi-modal framework, which fuses both structural and textual representation together to generate a joint multimodal representation of crystalline materials. We conduct extensive experiments on two benchmark datasets across ten different properties to show that CrysMMNet outperforms existing state-of-the-art baseline methods with a good margin. We also observe that fusing the textual representation with crystal graph structure provides consistent improvement for all the SOTA GNN models compared to their own vanilla versions. We have shared the textual dataset, that we have curated for both the benchmark material databases, with the community for future use..

Cite this Paper

BibTeX
@InProceedings{pmlr-v216-das23a, title = {{CrysMMNet}: Multimodal Representation for Crystal Property Prediction}, author = {Das, Kishalay and Goyal, Pawan and Lee, Seung-Cheol and Bhattacharjee, Satadeep and Ganguly, Niloy}, booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence}, pages = {507--517}, year = {2023}, editor = {Evans, Robin J. and Shpitser, Ilya}, volume = {216}, series = {Proceedings of Machine Learning Research}, month = {31 Jul--04 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v216/das23a/das23a.pdf}, url = {https://proceedings.mlr.press/v216/das23a.html}, abstract = {Machine Learning models have emerged as a powerful tool for fast and accurate prediction of different crystalline properties. Exiting state-of-the-art models rely on a single modality of crystal data i.e crystal graph structure, where they construct multi-graph by establishing edges between nearby atoms in 3D space and apply GNN to learn materials representation. Thereby, they encode local chemical semantics around the atoms successfully but fail to capture important global periodic structural information like space group number, crystal symmetry, rotational information etc, which influence different crystal properties. In this work, we leverage textual descriptions of materials to model global structural information into graph structure and learn a more robust and enriched representation of crystalline materials. To this effect, we first curate a textual dataset for crystalline material databases containing descriptions of each material. Further, we propose CrysMMNet, a simple multi-modal framework, which fuses both structural and textual representation together to generate a joint multimodal representation of crystalline materials. We conduct extensive experiments on two benchmark datasets across ten different properties to show that CrysMMNet outperforms existing state-of-the-art baseline methods with a good margin. We also observe that fusing the textual representation with crystal graph structure provides consistent improvement for all the SOTA GNN models compared to their own vanilla versions. We have shared the textual dataset, that we have curated for both the benchmark material databases, with the community for future use..} }
Endnote
%0 Conference Paper %T CrysMMNet: Multimodal Representation for Crystal Property Prediction %A Kishalay Das %A Pawan Goyal %A Seung-Cheol Lee %A Satadeep Bhattacharjee %A Niloy Ganguly %B Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2023 %E Robin J. Evans %E Ilya Shpitser %F pmlr-v216-das23a %I PMLR %P 507--517 %U https://proceedings.mlr.press/v216/das23a.html %V 216 %X Machine Learning models have emerged as a powerful tool for fast and accurate prediction of different crystalline properties. Exiting state-of-the-art models rely on a single modality of crystal data i.e crystal graph structure, where they construct multi-graph by establishing edges between nearby atoms in 3D space and apply GNN to learn materials representation. Thereby, they encode local chemical semantics around the atoms successfully but fail to capture important global periodic structural information like space group number, crystal symmetry, rotational information etc, which influence different crystal properties. In this work, we leverage textual descriptions of materials to model global structural information into graph structure and learn a more robust and enriched representation of crystalline materials. To this effect, we first curate a textual dataset for crystalline material databases containing descriptions of each material. Further, we propose CrysMMNet, a simple multi-modal framework, which fuses both structural and textual representation together to generate a joint multimodal representation of crystalline materials. We conduct extensive experiments on two benchmark datasets across ten different properties to show that CrysMMNet outperforms existing state-of-the-art baseline methods with a good margin. We also observe that fusing the textual representation with crystal graph structure provides consistent improvement for all the SOTA GNN models compared to their own vanilla versions. We have shared the textual dataset, that we have curated for both the benchmark material databases, with the community for future use..
APA
Das, K., Goyal, P., Lee, S., Bhattacharjee, S. & Ganguly, N.. (2023). CrysMMNet: Multimodal Representation for Crystal Property Prediction. Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 216:507-517 Available from https://proceedings.mlr.press/v216/das23a.html.

Related Material