Noise-robust Contrastive Learning for Critical Transition Detection in Dynamical Systems
This addresses the challenge of accurately identifying critical points in dynamical systems for scientific and engineering applications, though it appears incremental as it builds on existing contrastive learning techniques.
The paper tackled the problem of detecting critical transitions in noisy time-series data by proposing a neural network architecture with a semi-orthogonality-constrained training algorithm, resulting in a method that matches traditional contrastive learning performance while being more lightweight and noise-resistant.
Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often masked by high-amplitude stochastic variability. Standard contrastive learning approaches based on deep neural networks, while promising for detecting critical transitions, are often overparameterized and sensitive to irrelevant noise, leading to inaccurate identification of critical points. To address these limitations, we propose a neural network architecture, constructed using singular value decomposition technique, together with a strictly semi-orthogonality-constrained training algorithm, to enhance the performance of traditional contrastive learning. Extensive experiments demonstrate that the proposed method matches the performance of traditional contrastive learning techniques in identifying critical transitions, yet is considerably more lightweight and markedly more resistant to noise.