EEGDancer: Dynamic Emotion Latent Space Masked Modeling with Reinforcement Learning for EEG Continuous Emotion Prediction

2026-06-04

AI Summary

This work addresses the challenge of effectively modeling the continuous and dynamic evolution of emotional states in electroencephalography (EEG) signals, a task hindered by frame-wise regression paradigms and high-dimensional noise. To overcome these limitations, the authors propose a unified framework that formulates continuous emotion prediction as a sequential decision-making problem. The approach leverages a causal spatiotemporal vector-quantized variational autoencoder (VQ-VAE) to construct a structured latent emotional space, integrates a Transformer architecture for masked temporal modeling, and employs Soft Actor-Critic reinforcement learning to optimize emotion trajectories at the sequence level. Evaluated on the SEED, SEED-IV, and Long-Term Naturalistic Emotion datasets, the method significantly outperforms existing approaches, providing the first empirical validation of the efficacy of latent-space modeling combined with sequence-level trajectory optimization for continuous emotion recognition.

Abstract

Continuous electroencephalography (EEG) emotion prediction aims to model the temporal evolution of human emotional states from EEG signals. Unlike conventional discrete emotion recognition, continuous prediction requires capturing long-range temporal dependencies and coherent emotional dynamics. However, existing methods mainly rely on point-wise regression and directly model noisy high-dimensional EEG features, limiting their ability to characterize continuous emotional evolution.To address these challenges, we propose EEGDancer, a dynamic emotional latent space learning framework for continuous EEG emotion prediction. The framework integrates vector-quantized representation learning, masked temporal modeling, and reinforcement learning-based trajectory optimization into a unified architecture.Specifically, a causal spatiotemporal Vector-Quantization Variational Autoencoder (VQ-VAE) is designed to learn structured emotional prototypes and construct a discrete-continuous emotional latent space from EEG signals. Based on the learned latent representations, a Transformer-based masked dynamic modeling strategy captures long-range emotional dependencies and temporal evolution patterns. Furthermore, continuous emotion prediction is formulated as a sequential decision-making problem, and a Soft Actor-Critic (SAC) framework is introduced to optimize emotional prediction trajectories at the sequence level instead of frame-wise local fitting.Extensive experiments on the SEED, SEED-IV, and Long-Term Naturalistic Emotion datasets demonstrate that EEGDancer consistently outperforms existing machine learning and deep learning methods. Ablation studies further verify the effectiveness of the proposed latent space and reinforcement learning-based trajectory optimization for modeling continuous EEG emotional dynamics.

Problem

• continuous emotion prediction
• EEG
• temporal dependencies
• emotional dynamics
• latent space

Innovation

• Vector-Quantized VAE
• Masked Temporal Modeling
• Reinforcement Learning
• Continuous Emotion Prediction
• EEG Latent Space