Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks

TL;DR

This paper introduces Multi-Scale Temporal Homeostasis (MSTH), a biologically inspired framework that enhances neural network robustness and efficiency by integrating regulation across multiple temporal scales, leading to improved performance and stability.

Contribution

The paper proposes MSTH, a novel multi-scale temporal regulation system for neural networks, demonstrating its effectiveness across various benchmarks and outperforming existing models.

Findings

MSTH improves accuracy across molecular, graph, and image tasks.

MSTH eliminates catastrophic failures and enhances recovery from perturbations.

MSTH outperforms single-scale and state-of-the-art models in robustness and efficiency.

Abstract

Artificial neural networks achieve strong performance on benchmark tasks but remain fundamentally brittle under perturbations, limiting their deployment in real-world settings. In contrast, biological nervous systems sustain reliable function across decades through homeostatic regulation coordinated across multiple temporal scales. Inspired by this principle, this presents Multi-Scale Temporal Homeostasis (MSTH), a biologically grounded framework that integrates ultra-fast (5-ms), fast (2-s), medium (5-min) and slow (1-hrs) regulation into artificial networks. MSTH implements the cross-scale coordination system for artificial neural networks, providing a unified temporal hierarchy that moves beyond superficial biomimicry. The cross-scale coordination enhances computational efficiency through evolutionary-refined optimization mechanisms. Experiments across molecular, graph and image classification benchmarks show that MSTH consistently improves accuracy, eliminates catastrophic failures and enhances recovery from perturbations. Moreover, MSTH outperforms both single-scale bio-inspired models and established state-of-the-art methods, demonstrating generality across diverse domains. These findings establish cross-scale temporal coordination as a core principle for stabilizing artificial neural systems, positioning MSTH as a foundation for building robust, resilient and biologically faithful intelligence.