Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators

TL;DR

This paper introduces activation-based mutation operators for pruning autoencoders, demonstrating their effectiveness in single models but limited transferability in coevolutionary settings, highlighting the importance of population dynamics.

Contribution

The study proposes new activation-guided mutation operators for neural network pruning and evaluates their performance in both canonical and coevolutionary autoencoder training.

Findings

Activation-guided operators outperform random pruning in single autoencoder training.

In coevolutionary settings, random pruning surpasses guided pruning.

Population-driven strategies improve robustness and preserve system dynamics.

Abstract

This study explores a novel approach to neural network pruning using evolutionary computation, focusing on simultaneously pruning the encoder and decoder of an autoencoder. We introduce two new mutation operators that use layer activations to guide weight pruning. Our findings reveal that one of these activation-informed operators outperforms random pruning, resulting in more efficient autoencoders with comparable performance to canonically trained models. Prior work has established that autoencoder training is effective and scalable with a spatial coevolutionary algorithm that cooperatively coevolves a population of encoders with a population of decoders, rather than one autoencoder. We evaluate how the same activity-guided mutation operators transfer to this context. We find that random pruning is better than guided pruning, in the coevolutionary setting. This suggests activation-based guidance proves more effective in low-dimensional pruning environments, where constrained sample spaces can lead to deviations from true uniformity in randomization. Conversely, population-driven strategies enhance robustness by expanding the total pruning dimensionality, achieving statistically uniform randomness that better preserves system dynamics. We experiment with pruning according to different schedules and present best combinations of operator and schedule for the canonical and coevolving populations cases.