Connectome-Guided Automatic Learning Rates for Deep Networks

TL;DR

This paper introduces CG-ALR, a brain-inspired method that dynamically adjusts learning rates in deep networks based on functional connectomes derived from neuron co-activations, leading to improved training performance.

Contribution

It presents a novel connectome-guided approach for online adaptive learning rate adjustment in deep neural networks, inspired by brain connectivity reconfiguration.

Findings

Outperforms traditional SGD schedules

Adapts learning rates based on network stability

Enhances training efficiency and stability

Abstract

The human brain is highly adaptive: its functional connectivity reconfigures on multiple timescales during cognition and learning, enabling flexible information processing. By contrast, artificial neural networks typically rely on manually-tuned learning-rate schedules or generic adaptive optimizers whose hyperparameters remain largely agnostic to a model's internal dynamics. In this paper, we propose Connectome-Guided Automatic Learning Rate (CG-ALR) that dynamically constructs a functional connectome of the neural network from neuron co-activations at each training iteration and adjusts learning rates online as this connectome reconfigures. This connectomics-inspired mechanism adapts step sizes to the network's dynamic functional organization, slowing learning during unstable reconfiguration and accelerating it when stable organization emerges. Our results demonstrate that principles inspired by brain connectomes can inform the design of adaptive learning rates in deep learning, generally outperforming traditional SGD-based schedules and recent methods.