Graph-regularized losses grounded in Russell's circumplex raise best-case EEG emotion accuracy by up to 5.42% and cut non-adjacent misclassifications by up to 39% across transformer, hybrid, and GNN backbones.
Premier Journal of Science (2026)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph-Regularized Deep Learning for EEG-Based Emotion Recognition with Psychologically-Grounded Label Structure
Graph-regularized losses grounded in Russell's circumplex raise best-case EEG emotion accuracy by up to 5.42% and cut non-adjacent misclassifications by up to 39% across transformer, hybrid, and GNN backbones.