Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition

TL;DR

This paper introduces two novel regularization techniques, LVL and LGCL, to address label inconsistency in EEG emotion recognition, improving model accuracy, interpretability, and robustness across multiple neural architectures.

Contribution

It proposes innovative regularization strategies based on mathematical principles to mitigate timescale-dependent label inconsistency in EEG emotion recognition models.

Findings

Both regularizers outperform state-of-the-art baselines.

LVL achieves the best overall performance across models.

Methods enhance interpretability and robustness.

Abstract

In this work, we address the often-overlooked issue of Timescale Dependent Label Inconsistency (TsDLI) in training neural network models for EEG-based human emotion recognition. To mitigate TsDLI and enhance model generalization and explainability, we propose two novel regularization strategies: Local Variation Loss (LVL) and Local-Global Consistency Loss (LGCL). Both methods incorporate classical mathematical principles--specifically, functions of bounded variation and commute-time distances--within a graph theoretic framework. Complementing our regularizers, we introduce a suite of new evaluation metrics that better capture the alignment between temporally local predictions and their associated global emotion labels. We validate our approach through comprehensive experiments on two widely used EEG emotion datasets, DREAMER and DEAP, across a range of neural architectures including LSTM and transformer-based models. Performance is assessed using five distinct metrics encompassing both quantitative accuracy and qualitative consistency. Results consistently show that our proposed methods outperform state-of-the-art baselines, delivering superior aggregate performance and offering a principled trade-off between interpretability and predictive power under label inconsistency. Notably, LVL achieves the best aggregate rank across all benchmarked backbones and metrics, while LGCL frequently ranks the second, highlighting the effectiveness of our framework.