EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph

Kaicheng Fu, Changde Du, Jie Peng, Kunpeng Wang, Shuangchen Zhao, Xiaoyu Chen, Huiguang He
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:17746-17763, 2025.

Abstract

Emotion recognition systems face significant challenges in real-world applications, where novel emotion categories continually emerge and multiple emotions often co-occur. This paper introduces multi-label fine-grained class incremental emotion decoding, which aims to develop models capable of incrementally learning new emotion categories while maintaining the ability to recognize multiple concurrent emotions. We propose an Augmented Emotional Semantics Learning (AESL) framework to address two critical challenges: past- and future-missing partial label problems. AESL incorporates an augmented Emotional Relation Graph (ERG) for reliable soft label generation and affective dimension-based knowledge distillation for future-aware feature learning. We evaluate our approach on three datasets spanning brain activity and multimedia domains, demonstrating its effectiveness in decoding up to 28 fine-grained emotion categories. Results show that AESL significantly outperforms existing methods while effectively mitigating catastrophic forgetting. Our code is available at https://github.com/ChangdeDu/EmoGrowth.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-fu25b, title = {{E}mo{G}rowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph}, author = {Fu, Kaicheng and Du, Changde and Peng, Jie and Wang, Kunpeng and Zhao, Shuangchen and Chen, Xiaoyu and He, Huiguang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {17746--17763}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/fu25b/fu25b.pdf}, url = {https://proceedings.mlr.press/v267/fu25b.html}, abstract = {Emotion recognition systems face significant challenges in real-world applications, where novel emotion categories continually emerge and multiple emotions often co-occur. This paper introduces multi-label fine-grained class incremental emotion decoding, which aims to develop models capable of incrementally learning new emotion categories while maintaining the ability to recognize multiple concurrent emotions. We propose an Augmented Emotional Semantics Learning (AESL) framework to address two critical challenges: past- and future-missing partial label problems. AESL incorporates an augmented Emotional Relation Graph (ERG) for reliable soft label generation and affective dimension-based knowledge distillation for future-aware feature learning. We evaluate our approach on three datasets spanning brain activity and multimedia domains, demonstrating its effectiveness in decoding up to 28 fine-grained emotion categories. Results show that AESL significantly outperforms existing methods while effectively mitigating catastrophic forgetting. Our code is available at https://github.com/ChangdeDu/EmoGrowth.} }
Endnote
%0 Conference Paper %T EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph %A Kaicheng Fu %A Changde Du %A Jie Peng %A Kunpeng Wang %A Shuangchen Zhao %A Xiaoyu Chen %A Huiguang He %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-fu25b %I PMLR %P 17746--17763 %U https://proceedings.mlr.press/v267/fu25b.html %V 267 %X Emotion recognition systems face significant challenges in real-world applications, where novel emotion categories continually emerge and multiple emotions often co-occur. This paper introduces multi-label fine-grained class incremental emotion decoding, which aims to develop models capable of incrementally learning new emotion categories while maintaining the ability to recognize multiple concurrent emotions. We propose an Augmented Emotional Semantics Learning (AESL) framework to address two critical challenges: past- and future-missing partial label problems. AESL incorporates an augmented Emotional Relation Graph (ERG) for reliable soft label generation and affective dimension-based knowledge distillation for future-aware feature learning. We evaluate our approach on three datasets spanning brain activity and multimedia domains, demonstrating its effectiveness in decoding up to 28 fine-grained emotion categories. Results show that AESL significantly outperforms existing methods while effectively mitigating catastrophic forgetting. Our code is available at https://github.com/ChangdeDu/EmoGrowth.
APA
Fu, K., Du, C., Peng, J., Wang, K., Zhao, S., Chen, X. & He, H.. (2025). EmoGrowth: Incremental Multi-label Emotion Decoding with Augmented Emotional Relation Graph. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:17746-17763 Available from https://proceedings.mlr.press/v267/fu25b.html.

Related Material