Preprocessing and Representation Learning for EEG Artifact Mitigation: A Review and Synergy Analysis

Electroencephalography (EEG) is widely used in brain–computer interfaces and clinical diagnosis, yet its low amplitude makes it highly vulnerable to artifacts that degrade downstream analysis. Existing EEG denoising approaches can be broadly grouped into two paradigms: (i) data-driven denoising methods that explicitly separate and remove noise components, and (ii) feature-learning methods that seek noise-robust latent representations directly from raw signals. This survey reviews recent progress in both paradigms, with a particular focus on integrating classical signal-processing principles with self-supervised learning (SSL). We argue that such integration can improve denoising effectiveness while enhancing interpretability and robustness under cross-subject, cross-device, and low signal-to-noise ratio (SNR) conditions. Specifically, we summarize representative techniques and their assumptions, propose a two-level taxonomy organized by denoising logic and technical paradigm, and provide supplementary experiments that benchmark traditional denoising modules within large EEG modeling pipelines. We further summarize practitioner-oriented guidelines to facilitate task- and data-adaptive preprocessing--SSL pipeline selection. Finally, we discuss open challenges and future directions toward hybrid denoising frameworks that combine signal-processing priors with deep neural networks.