CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials

• URL: http://arxiv.org/abs/2301.05852v1
• Date: Sat, 14 Jan 2023 08:12:01 GMT
• Title: CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials
• Authors: Kishalay Das, Bidisha Samanta, Pawan Goyal, Seung-Cheol Lee, Satadeep Bhattacharjee and Niloy Ganguly
• Abstract summary: This paper presents CrysGNN, a new pre-trained GNN framework for crystalline materials. It captures both node and graph level structural information of crystal graphs using unlabelled material data. We conduct extensive experiments to show that with distilled knowledge from the pre-trained model, all the SOTA algorithms are able to outperform their own vanilla version with good margins.
• Score: 25.622724168215097
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, graph neural network (GNN) based approaches have emerged as a powerful technique to encode complex topological structure of crystal materials in an enriched representation space. These models are often supervised in nature and using the property-specific training data, learn relationship between crystal structure and different properties like formation energy, bandgap, bulk modulus, etc. Most of these methods require a huge amount of property-tagged data to train the system which may not be available for different properties. However, there is an availability of a huge amount of crystal data with its chemical composition and structural bonds. To leverage these untapped data, this paper presents CrysGNN, a new pre-trained GNN framework for crystalline materials, which captures both node and graph level structural information of crystal graphs using a huge amount of unlabelled material data. Further, we extract distilled knowledge from CrysGNN and inject into different state of the art property predictors to enhance their property prediction accuracy. We conduct extensive experiments to show that with distilled knowledge from the pre-trained model, all the SOTA algorithms are able to outperform their own vanilla version with good margins. We also observe that the distillation process provides a significant improvement over the conventional approach of finetuning the pre-trained model. We have released the pre-trained model along with the large dataset of 800K crystal graph which we carefully curated; so that the pretrained model can be plugged into any existing and upcoming models to enhance their prediction accuracy.

Related papers

• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• On the Stability of Iterative Retraining of Generative Models on their own Data [56.153542044045224]
  We study the impact of training generative models on mixed datasets. We first prove the stability of iterative training under the condition that the initial generative models approximate the data distribution well enough. We empirically validate our theory on both synthetic and natural images by iteratively training normalizing flows and state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-09-30T16:41:04Z)
• DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials [0.0]
  We propose DeepCrysTet, a novel deep learning approach for predicting material properties. DeepCrysTet uses crystal structures represented as a 3D tetrahedral mesh generated by Delaunay tetrahedralization. Experiments show that DeepCrysTet significantly outperforms existing GNN models in classifying crystal structures and state-of-the-art performance in predicting elastic properties.
  arXiv  Detail & Related papers  (2023-09-07T05:23:52Z)
• Substitutional Alloying Using Crystal Graph Neural Networks [0.0]
  Graph Neural Networks (GNNs) allow for direct learning representations on graphs, such as the ones formed by crystals. We use CGNNs to predict crystal properties with DFT level accuracy, through graphs with encoding of the atomic (node/vertex), bond (edge), and global state attributes. We perform DFT validation to assess the accuracy in the prediction of formation energies and structural features.
  arXiv  Detail & Related papers  (2023-06-19T08:18:17Z)
• CrysMMNet: Multimodal Representation for Crystal Property Prediction [22.576167897068956]
  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.
  arXiv  Detail & Related papers  (2023-06-09T11:16:01Z)
• Generalizing Dataset Distillation via Deep Generative Prior [75.9031209877651]
  We propose to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given to a learning algorithm as training data, result in a model approximating one trained on the original data. We present a new optimization algorithm that distills a large number of images into a few intermediate feature vectors in the generative model's latent space.
  arXiv  Detail & Related papers  (2023-05-02T17:59:31Z)
• Graph Contrastive Learning for Materials [6.667711415870472]
  We introduce CrystalCLR, a framework for constrastive learning of representations with crystal graph neural networks. With the addition of a novel loss function, our framework is able to learn representations competitive with engineered fingerprinting methods. We also demonstrate that via model finetuning, contrastive pretraining can improve the performance of graph neural networks for prediction of material properties.
  arXiv  Detail & Related papers  (2022-11-24T04:15:47Z)
• Data-Free Adversarial Knowledge Distillation for Graph Neural Networks [62.71646916191515]
  We propose the first end-to-end framework for data-free adversarial knowledge distillation on graph structured data (DFAD-GNN) To be specific, our DFAD-GNN employs a generative adversarial network, which mainly consists of three components: a pre-trained teacher model and a student model are regarded as two discriminators, and a generator is utilized for deriving training graphs to distill knowledge from the teacher model into the student model. Our DFAD-GNN significantly surpasses state-of-the-art data-free baselines in the graph classification task.
  arXiv  Detail & Related papers  (2022-05-08T08:19:40Z)
• Crystal Twins: Self-supervised Learning for Crystalline Material Property Prediction [8.048439531116367]
  We introduce Crystal Twins (CT): an SSL method for crystalline materials property prediction. We pre-train a Graph Neural Network (GNN) by applying the redundancy reduction principle to the graph latent embeddings of augmented instances. By sharing the pre-trained weights when fine-tuning the GNN for regression tasks, we significantly improve the performance for 7 challenging material property prediction benchmarks.
  arXiv  Detail & Related papers  (2022-05-04T05:08:46Z)
• Incorporating Causal Graphical Prior Knowledge into Predictive Modeling via Simple Data Augmentation [92.96204497841032]
  Causal graphs (CGs) are compact representations of the knowledge of the data generating processes behind the data distributions. We propose a model-agnostic data augmentation method that allows us to exploit the prior knowledge of the conditional independence (CI) relations. We experimentally show that the proposed method is effective in improving the prediction accuracy, especially in the small-data regime.
  arXiv  Detail & Related papers  (2021-02-27T06:13:59Z)
• A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning [49.86828302591469]
  We train >35,000 neural network models, sweeping over common featurization techniques. We found the RNA-seq to be highly redundant and informative even with subsets larger than 128 features.
  arXiv  Detail & Related papers  (2020-04-30T20:42:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.