Motivation is Something You Need

TL;DR

This paper introduces a dual-model training paradigm inspired by affective neuroscience, where a smaller base model is enhanced by a larger motivated model activated under specific conditions, improving performance and efficiency.

Contribution

The novel dual-model framework mimics emotional motivation states to enhance training, enabling shared weights and selective capacity expansion, leading to improved model performance.

Findings

Alternating training scheme improves base model accuracy.

Motivated larger model can outperform standalone models.

Training cost is reduced compared to training larger models alone.

Abstract

This work introduces a novel training paradigm that draws from affective neuroscience. Inspired by the interplay of emotions and cognition in the human brain and more specifically the SEEKING motivational state, we design a dual-model framework where a smaller base model is trained continuously, while a larger motivated model is activated intermittently during predefined "motivation conditions". The framework mimics the emotional state of high curiosity and anticipation of reward in which broader brain regions are recruited to enhance cognitive performance. Exploiting scalable architectures where larger models extend smaller ones, our method enables shared weight updates and selective expansion of network capacity during noteworthy training steps. Empirical evaluation on the image classification task demonstrates that, not only does the alternating training scheme efficiently and effectively enhance the base model compared to a traditional scheme, in some cases, the motivational model also surpasses its standalone counterpart despite seeing less data per epoch. This opens the possibility of simultaneously training two models tailored to different deployment constraints with competitive or superior performance while keeping training cost lower than when training the larger model.