Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911055904505856 |
|---|---|
| author | Zeng, Xiaocong Michoski, Craig Pang, Yan Kuang, Dongyang |
| author_facet | Zeng, Xiaocong Michoski, Craig Pang, Yan Kuang, Dongyang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10895 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition Zeng, Xiaocong Michoski, Craig Pang, Yan Kuang, Dongyang Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Signal Processing 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. |
| title | Commuting Distance Regularization for Timescale-Dependent Label Inconsistency in EEG Emotion Recognition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2507.10895 |