# Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification

arXiv: https://arxiv.org/abs/2601.07858 · HTML: https://mlsanity.com/paper/2601.07858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Limitations of the Empirical Fisher Approximation for Natural Gradient Descent](https://mlsanity.com/paper/1905.12558/) (2019)
- [Revisiting Natural Gradient for Deep Networks](https://mlsanity.com/paper/1301.3584/) (2013)
- [Deep learning-based electroencephalography analysis: a systematic review](https://mlsanity.com/paper/1901.05498/) (2019)
- [On Quadratic Penalties in Elastic Weight Consolidation](https://mlsanity.com/paper/1712.03847/) (2017)
- [A Statistical Theory of Regularization-Based Continual Learning](https://mlsanity.com/paper/2406.06213/) (2024)
- [Toward cross-subject and cross-session generalization in EEG-based emotion recognition: Systematic review, taxonomy, and methods](https://mlsanity.com/paper/2212.08744/) (2022)
- [On the Computation of the Fisher Information in Continual Learning](https://mlsanity.com/paper/2502.11756/) (2025)
- [Evaluation of Regularization-based Continual Learning Approaches: Application to HAR](https://mlsanity.com/paper/2304.13327/) (2023)
- [Personalized Continual EEG Decoding: Retaining and Transferring Knowledge](https://mlsanity.com/paper/2411.11874/) (2024)
- [Robust Emotion Recognition via Bi-Level Self-Supervised Continual Learning](https://mlsanity.com/paper/2505.10575/) (2025)

## Built on by (most cited first, 1 of 1)

- [Do Artificial Neural Networks Need Dendritic Nanotubes? Two Reasons for Shrinking Importance Estimates in Continual Learning](https://mlsanity.com/paper/2610.14258/) (2026)

## Abstract (arXiv)

Generalisation to unseen subjects in EEG-based emotion classification remains a challenge due to high inter-and intra-subject variability. Continual learning (CL) poses a promising solution by learning from a sequence of tasks while mitigating catastrophic forgetting. Regularisation-based CL approaches, such as Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), and Memory Aware Synapses (MAS), are commonly used as baselines in EEG-based CL studies, yet their suitability for this problem remains underexplored. This study theoretically and empirically finds that regularisation-based CL methods show limited performance for EEG-based emotion classification on the DREAMER and SEED datasets. We identify a fundamental misalignment in the stability-plasticity trade-off, where regularisation-based methods prioritise mitigating catastrophic forgetting (backward transfer) over adapting to new subjects (forward transfer). We investigate this limitation under subject-incremental sequences and observe that: (1) the heuristics for estimating parameter importance become less reliable under noisy data and covariate shift, (2) gradients on parameters deemed important by these heuristics often interfere with gradient updates required for new subjects, moving optimisation away from the minimum, (3) importance values accumulated across tasks over-constrain the model, and (4) performance is sensitive to subject order. Forward transfer showed no statistically significant improvement over sequential fine-tuning (p > 0.05 across approaches and datasets). The high variability of EEG signals means past subjects provide limited value to future subjects. Regularisation-based continual learning approaches are therefore limited for robust generalisation to unseen subjects in EEG-based emotion classification.