Deep Extrapolation for Attribute-Enhanced Generation

Alvin Chan, Ali Madani, Ben Krause, Nikhil Naik

Keywords: extrapolation, generative modeling, controllable generation, protein design

TL;DR: How do we generate sequences that extrapolate beyond the training distribution?

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.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

Code: https://github.com/salesforce/genhance

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2107.02968/code)