# Molecular Attributes Transfer from Non-Parallel Data

arXiv: https://arxiv.org/abs/2111.15146 · HTML: https://mlsanity.com/paper/2111.15146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 30 Nov 2021.

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Improving Variational Inference with Inverse Autoregressive Flow](https://mlsanity.com/paper/1606.04934/) (2016)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [MADE: Masked Autoencoder for Distribution Estimation](https://mlsanity.com/paper/1502.03509/) (2015)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Disentangled Representation Learning for Non-Parallel Text Style Transfer](https://mlsanity.com/paper/1808.04339/) (2018)
- [Syntax-Directed Variational Autoencoder for Structured Data](https://mlsanity.com/paper/1802.08786/) (2018)
- [Multi-Objective De Novo Drug Design with Conditional Graph Generative Model](https://mlsanity.com/paper/1801.07299/) (2018)
- [Learning Multimodal Graph-to-Graph Translation for Molecular Optimization](https://mlsanity.com/paper/1812.01070/) (2018)
- [Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation](https://mlsanity.com/paper/1905.05621/) (2019)
- [Guided Variational Autoencoder for Disentanglement Learning](https://mlsanity.com/paper/2004.01255/) (2020)
- [Toward Diverse Text Generation with Inverse Reinforcement Learning](https://mlsanity.com/paper/1804.11258/) (2018)
- [CORE: Automatic Molecule Optimization Using Copy & Refine Strategy](https://mlsanity.com/paper/1912.05910/) (2019)
- [Robust Front-End for Multi-Channel ASR using Flow-Based Density Estimation](https://mlsanity.com/paper/2007.12903/) (2020)

## Abstract (arXiv)

Optimizing chemical molecules for desired properties lies at the core of drug development. Despite initial successes made by deep generative models and reinforcement learning methods, these methods were mostly limited by the requirement of predefined attribute functions or parallel data with manually pre-compiled pairs of original and optimized molecules. In this paper, for the first time, we formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data through adversarial training strategies. Our model further enables both preservation of molecular contents and optimization of molecular properties through combining auxiliary guided-variational autoencoders and generative flow techniques. Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.