DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
Read the original on arXiv Machine Learning →The paper introduces Diffusion-Conditioned Representation Alignment (DCRA), a training framework that uses the forward diffusion process as a structured corruption scheduler for time‑series representation learning. DCRA aligns representations across noise levels with a feature‑level consistency objective, preserving class‑discriminative structure and enabling smooth, semantically coherent trajectories in latent space. Experiments on the CHB‑MIT EEG dataset demonstrate that DCRA improves seizure detection performance under various noise conditions, achieving higher sensitivity at low false‑positive rates and producing more balanced, structured representations than baseline methods.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.