Meta-autoencoders: An approach to discovery and representation of relationships between dynamically evolving classes
This is an incremental approach for researchers in machine learning and biology interested in representing evolving classes, but it lacks empirical validation.
The paper introduces meta-autoencoders (MAEs) as neural networks that learn compact representations for collections of autoencoders, aiming to model relationships between dynamically evolving classes, such as species in natural evolution, but provides only initial examples and definitions without concrete results or numbers.
An autoencoder (AE) is a neural network that, using self-supervised training, learns a succinct parameterized representation, and a corresponding encoding and decoding process, for all instances in a given class. Here, we introduce the concept of a meta-autoencoder (MAE): an AE for a collection of autoencoders. Given a family of classes that differ from each other by the values of some parameters, and a trained AE for each class, an MAE for the family is a neural net that has learned a compact representation and associated encoder and decoder for the class-specific AEs. One application of this general concept is in research and modeling of natural evolution -- capturing the defining and the distinguishing properties across multiple species that are dynamically evolving from each other and from common ancestors. In this interim report we provide a constructive definition of MAEs, initial examples, and the motivating research directions in machine learning and biology.