Deep Extrapolation for Attribute-Enhanced Generation
Abstract
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. Trained on movie reviews and a computed protein stability dataset, GENhance can generate strongly-positive text reviews and highly stable protein sequences without being exposed to similar data during training. We release our benchmark tasks and models to contribute to the study of generative modeling extrapolation and data-driven design in biology and chemistry.
Cite
Text
Chan et al. "Deep Extrapolation for Attribute-Enhanced Generation." Neural Information Processing Systems, 2021.Markdown
[Chan et al. "Deep Extrapolation for Attribute-Enhanced Generation." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/chan2021neurips-deep/)BibTeX
@inproceedings{chan2021neurips-deep,
title = {{Deep Extrapolation for Attribute-Enhanced Generation}},
author = {Chan, Alvin and Madani, Ali and Krause, Ben and Naik, Nikhil},
booktitle = {Neural Information Processing Systems},
year = {2021},
url = {https://mlanthology.org/neurips/2021/chan2021neurips-deep/}
}