Connectome-Guided Optimization for Deep Networks

Peilin He, Tananun Songdechakraiwut
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:3295-3303, 2026.

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, with particularly consistent improvements over traditional SGD-based schedules and competitive performance against Adam-family scheduled baselines and recent adaptive methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-he26b, title = { Connectome-Guided Optimization for Deep Networks }, author = {He, Peilin and Songdechakraiwut, Tananun}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {3295--3303}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/he26b/he26b.pdf}, url = {https://proceedings.mlr.press/v300/he26b.html}, 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, with particularly consistent improvements over traditional SGD-based schedules and competitive performance against Adam-family scheduled baselines and recent adaptive methods. } }
Endnote
%0 Conference Paper %T Connectome-Guided Optimization for Deep Networks %A Peilin He %A Tananun Songdechakraiwut %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-he26b %I PMLR %P 3295--3303 %U https://proceedings.mlr.press/v300/he26b.html %V 300 %X 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, with particularly consistent improvements over traditional SGD-based schedules and competitive performance against Adam-family scheduled baselines and recent adaptive methods.
APA
He, P. & Songdechakraiwut, T.. (2026). Connectome-Guided Optimization for Deep Networks . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:3295-3303 Available from https://proceedings.mlr.press/v300/he26b.html.

Related Material