Accelerating the inference of string generation-based chemical reaction models for industrial applications

• URL: http://arxiv.org/abs/2407.09685v2
• Date: Wed, 17 Jul 2024 10:43:17 GMT
• Title: Accelerating the inference of string generation-based chemical reaction models for industrial applications
• Authors: Mikhail Andronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber, Djork-Arné Clevert,
• Abstract summary: We present a method to accelerate inference in autoregressive SMILES generators through speculative decoding. We achieve over 3X faster inference in reaction prediction and single-step retrosynthesis, with no loss in accuracy.
• Score: 25.069344340760715
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-art accuracy. However, they suffer from slow inference speed. We present a method to accelerate inference in autoregressive SMILES generators through speculative decoding by copying query string subsequences into target strings in the right places. We apply our method to the molecular transformer implemented in Pytorch Lightning and achieve over 3X faster inference in reaction prediction and single-step retrosynthesis, with no loss in accuracy.

Related papers

• Autoregressive Speech Synthesis without Vector Quantization [135.4776759536272]
  We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS) MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition.
  arXiv  Detail & Related papers  (2024-07-11T14:36:53Z)
• Retrosynthesis prediction enhanced by in-silico reaction data augmentation [66.5643280109899]
  We present RetroWISE, a framework that employs a base model inferred from real paired data to perform in-silico reaction generation and augmentation. On three benchmark datasets, RetroWISE achieves the best overall performance against state-of-the-art models.
  arXiv  Detail & Related papers  (2024-01-31T07:40:37Z)
• Synthetic Wave-Geometric Impulse Responses for Improved Speech Dereverberation [69.1351513309953]
  We show that accurately simulating the low-frequency components of Room Impulse Responses (RIRs) is important to achieving good dereverberation. We demonstrate that speech dereverberation models trained on hybrid synthetic RIRs outperform models trained on RIRs generated by prior geometric ray tracing methods.
  arXiv  Detail & Related papers  (2022-12-10T20:15:23Z)
• Root-aligned SMILES for Molecular Retrosynthesis Prediction [31.818364437526885]
  Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to discover precursor molecules that can be used to synthesize a target molecule. A popular paradigm of existing computational retrosynthesis methods formulate retrosynthesis prediction as a sequence-to-sequence translation problem. We propose the root-aligned SMILES(R-SMILES), which specifies a tightly aligned one-to-one mapping between the product and the reactant SMILES.
  arXiv  Detail & Related papers  (2022-03-22T03:50:04Z)
• Retroformer: Pushing the Limits of Interpretable End-to-end Retrosynthesis Transformer [15.722719721123054]
  Retrosynthesis prediction is one of the fundamental challenges in organic synthesis. We propose Retroformer, a novel Transformer-based architecture for retrosynthesis prediction. Retroformer reaches the new state-of-the-art accuracy for the end-to-end template-free retrosynthesis.
  arXiv  Detail & Related papers  (2022-01-29T02:03:55Z)
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction [26.007965383304864]
  We devise a non-autoregressive learning paradigm that predicts reaction in one shot. We formulate a reaction as an arbitrary electron flow and predict it with a novel multi-pointer decoding network. Experiments on the USPTO-MIT dataset show that our approach has established a new state-of-the-art top-1 accuracy.
  arXiv  Detail & Related papers  (2021-06-08T16:39:08Z)
• FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization [72.9385528828306]
  A typical transducer model decodes the output sequence conditioned on the current acoustic state. The number of blank tokens in the prediction results accounts for nearly 90% of all tokens. We propose a method named fast-skip regularization, which tries to align the blank position predicted by a transducer with that predicted by a CTC model.
  arXiv  Detail & Related papers  (2021-04-07T03:15:10Z)
• Non-autoregressive electron flow generation for reaction prediction [15.98143959075733]
  We devise a novel decoder that avoids such sequential generating and predicts the reaction in a Non-Autoregressive manner. Inspired by physical-chemistry insights, we represent edge edits in a molecule graph as electron flows, which can then be predicted in parallel. Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.
  arXiv  Detail & Related papers  (2020-12-16T10:01:26Z)
• RetroXpert: Decompose Retrosynthesis Prediction like a Chemist [60.463900712314754]
  We devise a novel template-free algorithm for automatic retrosynthetic expansion. Our method disassembles retrosynthesis into two steps. While outperforming the state-of-the-art baselines, our model also provides chemically reasonable interpretation.
  arXiv  Detail & Related papers  (2020-11-04T04:35:34Z)
• Synthesizer: Rethinking Self-Attention in Transformer Models [93.08171885200922]
  dot product self-attention is central and indispensable to state-of-the-art Transformer models. This paper investigates the true importance and contribution of the dot product-based self-attention mechanism on the performance of Transformer models.
  arXiv  Detail & Related papers  (2020-05-02T08:16:19Z)

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.