Extreme Acceleration of Graph Neural Network-based Prediction Models for Quantum Chemistry

• URL: http://arxiv.org/abs/2211.13853v1
• Date: Fri, 25 Nov 2022 01:30:18 GMT
• Title: Extreme Acceleration of Graph Neural Network-based Prediction Models for Quantum Chemistry
• Authors: Hatem Helal, Jesun Firoz, Jenna Bilbrey, Mario Michael Krell, Tom Murray, Ang Li, Sotiris Xantheas, Sutanay Choudhury
• Abstract summary: We present a novel hardware-software co-design approach to scale up the training of graph neural networks for molecular property prediction. We introduce an algorithm to coalesce the batches of molecular graphs into fixed size packs to eliminate redundant computation and memory. We demonstrate that such a co-design approach can reduce the training time of such molecular property prediction models from days to less than two hours.
• Score: 7.592530794455257
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Molecular property calculations are the bedrock of chemical physics. High-fidelity \textit{ab initio} modeling techniques for computing the molecular properties can be prohibitively expensive, and motivate the development of machine-learning models that make the same predictions more efficiently. Training graph neural networks over large molecular databases introduces unique computational challenges such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs such as social networks. This paper demonstrates a novel hardware-software co-design approach to scale up the training of graph neural networks for molecular property prediction. We introduce an algorithm to coalesce the batches of molecular graphs into fixed size packs to eliminate redundant computation and memory associated with alternative padding techniques and improve throughput via minimizing communication. We demonstrate the effectiveness of our co-design approach by providing an implementation of a well-established molecular property prediction model on the Graphcore Intelligence Processing Units (IPU). We evaluate the training performance on multiple molecular graph databases with varying degrees of graph counts, sizes and sparsity. We demonstrate that such a co-design approach can reduce the training time of such molecular property prediction models from days to less than two hours, opening new possibilities for AI-driven scientific discovery.

Related papers

• GraphXForm: Graph transformer for computer-aided molecular design with application to extraction [73.1842164721868]
  We present GraphXForm, a decoder-only graph transformer architecture, which is pretrained on existing compounds and then fine-tuned. We evaluate it on two solvent design tasks for liquid-liquid extraction, showing that it outperforms four state-of-the-art molecular design techniques.
  arXiv  Detail & Related papers  (2024-11-03T19:45:15Z)
• GraphBPE: Molecular Graphs Meet Byte-Pair Encoding [12.985482706851846]
  We propose GraphBPE, which tokenizes a molecular graph into different substructures and acts as a preprocessing schedule independent of the model architectures. Our experiments on 3 graph-level classification and 3 graph-level regression datasets show that data preprocessing could boost the performance of models for molecular graphs.
  arXiv  Detail & Related papers  (2024-07-26T18:45:09Z)
• CTAGE: Curvature-Based Topology-Aware Graph Embedding for Learning Molecular Representations [11.12640831521393]
  We propose an embedding approach CTAGE, utilizing $k$-hop discrete Ricci curvature to extract structural insights from molecular graph data. Results indicate that introducing node curvature significantly improves the performance of current graph neural network frameworks.
  arXiv  Detail & Related papers  (2023-07-25T06:13:01Z)
• Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular Property Prediction [53.06671763877109]
  We develop molecular embeddings that encode complex molecular characteristics to improve the performance of few-shot molecular property prediction. Our approach leverages large amounts of synthetic data, namely the results of molecular docking calculations. On multiple molecular property prediction benchmarks, training from the embedding space substantially improves Multi-Task, MAML, and Prototypical Network few-shot learning performance.
  arXiv  Detail & Related papers  (2023-02-04T01:32:40Z)
• ViSNet: an equivariant geometry-enhanced graph neural network with vector-scalar interactive message passing for molecules [69.05950120497221]
  We propose an equivariant geometry-enhanced graph neural network called ViSNet, which elegantly extracts geometric features and efficiently models molecular structures. Our proposed ViSNet outperforms state-of-the-art approaches on multiple MD benchmarks, including MD17, revised MD17 and MD22, and achieves excellent chemical property prediction on QM9 and Molecule3D datasets.
  arXiv  Detail & Related papers  (2022-10-29T07:12:46Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction [13.55018269009361]
  We introduce Knowledge-guided Pre-training of Graph Transformer (KPGT), a novel self-supervised learning framework for molecular graph representation learning. KPGT can offer superior performance over current state-of-the-art methods on several molecular property prediction tasks.
  arXiv  Detail & Related papers  (2022-06-02T08:22:14Z)
• Attention-wise masked graph contrastive learning for predicting molecular property [15.387677968070912]
  We proposed a self-supervised representation learning framework for large-scale unlabeled molecules. We developed a novel molecular graph augmentation strategy, referred to as attention-wise graph mask. Our model can capture important molecular structure and higher-order semantic information.
  arXiv  Detail & Related papers  (2022-05-02T00:28:02Z)
• Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discovery [53.00288162642151]
  We develop MoleculeKit, a suite of comprehensive machine learning tools spanning different computational models and molecular representations. Built on these representations, MoleculeKit includes both deep learning and traditional machine learning methods for graph and sequence data. Results on both online and offline antibiotics discovery and molecular property prediction tasks show that MoleculeKit achieves consistent improvements over prior methods.
  arXiv  Detail & Related papers  (2020-12-02T02:09:31Z)
• Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder [0.0]
  We develop a molecular generative model based on variational inference and graph theory in the small data regime. The model's performance is evaluated by generating molecules with desired target properties.
  arXiv  Detail & Related papers  (2020-09-29T09:05:27Z)
• Self-Supervised Graph Transformer on Large-Scale Molecular Data [73.3448373618865]
  We propose a novel framework, GROVER, for molecular representation learning. GROVER can learn rich structural and semantic information of molecules from enormous unlabelled molecular data. We pre-train GROVER with 100 million parameters on 10 million unlabelled molecules -- the biggest GNN and the largest training dataset in molecular representation learning.
  arXiv  Detail & Related papers  (2020-06-18T08:37:04Z)

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.