# Robust Emotion Recognition via Bi-Level Self-Supervised Continual Learning

arXiv: https://arxiv.org/abs/2505.10575 · HTML: https://mlsanity.com/paper/2505.10575/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 57 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 18 of 18)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering](https://mlsanity.com/paper/1611.05148/) (2016)
- [Limitations of the Empirical Fisher Approximation for Natural Gradient Descent](https://mlsanity.com/paper/1905.12558/) (2019)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [Self-supervised Learning is More Robust to Dataset Imbalance](https://mlsanity.com/paper/2110.05025/) (2021)
- [Self-supervised ECG Representation Learning for Emotion Recognition](https://mlsanity.com/paper/2002.03898/) (2020)
- [Contrastive Learning for Unsupervised Domain Adaptation of Time Series](https://mlsanity.com/paper/2206.06243/) (2022)
- [Improving Task-free Continual Learning by Distributionally Robust Memory Evolution](https://mlsanity.com/paper/2207.07256/) (2022)
- [GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition](https://mlsanity.com/paper/2109.03124/) (2021)
- [Transformer-based Self-supervised Multimodal Representation Learning for Wearable Emotion Recognition](https://mlsanity.com/paper/2303.17611/) (2023)
- [Transformer-Based Self-Supervised Learning for Emotion Recognition](https://mlsanity.com/paper/2204.05103/) (2022)
- [SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledge](https://mlsanity.com/paper/2208.11266/) (2022)
- [Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams](https://mlsanity.com/paper/2204.12193/) (2022)

## Built on by (most cited first, 2 of 2)

- [Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification](https://mlsanity.com/paper/2601.07858/) (2026)
- [Adaptive XAI in High Stakes Environments: Modeling Swift Trust with Multimodal Feedback in Human AI Teams](https://mlsanity.com/paper/2507.21158/) (2025)

## Abstract (arXiv)

Emotion recognition through physiological signals such as electroencephalogram (EEG) has become an essential aspect of affective computing and provides an objective way to capture human emotions. However, physiological data characterized by cross-subject variability and noisy labels hinder the performance of emotion recognition models. Existing domain adaptation and continual learning methods struggle to address these issues, especially under realistic conditions where data is continuously streamed and unlabeled. To overcome these limitations, we propose a novel bi-level self-supervised continual learning framework, SSOCL, based on a dynamic memory buffer. This bi-level architecture iteratively refines the dynamic buffer and pseudo-label assignments to effectively retain representative samples, enabling generalization from continuous, unlabeled physiological data streams for emotion recognition. The assigned pseudo-labels are subsequently leveraged for accurate emotion prediction. Key components of the framework, including a fast adaptation module and a cluster-mapping module, enable robust learning and effective handling of evolving data streams. Experimental validation on two mainstream EEG tasks demonstrates the framework's ability to adapt to continuous data streams while maintaining strong generalization across subjects, outperforming existing approaches.