QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis. Zhu, Y., Jiang, Y., Jiang, G., Hou, B., Zhou, P. Y., Lin, G., & Wang, Y. In Liakata, M., Moreira, V. P., Zhang, J., & Jurgens, D., editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 31689–31703, San Diego, California, United States, July, 2026. Association for Computational Linguistics.
QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis [link]Paper  abstract   bibtex   
Multimodal Sentiment Analysis (MSA) aims to infer human sentiment from textual, acoustic, and visual signals. In real-world scenarios, however, multimodal inputs are often compromised by dynamic noise or modality missingness. Existing methods typically treat these imperfections as discrete cases or assume fixed corruption ratios, which limits their adaptability to continuously varying reliability conditions. To address this, we first introduce a Continuous Reliability Spectrum to unify missingness and quality degradation into a single framework. Building on this, we propose QA-MoE, a Quality-Aware Mixture-of-Experts framework that quantifies modality reliability via self-supervised aleatoric uncertainty. This mechanism explicitly guides expert routing, enabling the model to suppress error propagation from unreliable signals while preserving task-relevant information. Extensive experiments indicate that QA-MoE achieves competitive or state-of-the-art performance across diverse degradation scenarios and exhibits a promising One-Checkpoint-for-All property in practice.
@inproceedings{zhu_qa-moe:_2026,
	address = {San Diego, California, United States},
	title = {{QA}-{MoE}: {Towards} a {Continuous} {Reliability} {Spectrum} with {Quality}-{Aware} {Mixture} of {Experts} for {Robust} {Multimodal} {Sentiment} {Analysis}},
	isbn = {979-8-89176-390-6},
	url = {https://aclanthology.org/2026.acl-long.1461/},
	abstract = {Multimodal Sentiment Analysis (MSA) aims to infer human sentiment from textual, acoustic, and visual signals. In real-world scenarios, however, multimodal inputs are often compromised by dynamic noise or modality missingness. Existing methods typically treat these imperfections as discrete cases or assume fixed corruption ratios, which limits their adaptability to continuously varying reliability conditions. To address this, we first introduce a Continuous Reliability Spectrum to unify missingness and quality degradation into a single framework. Building on this, we propose QA-MoE, a Quality-Aware Mixture-of-Experts framework that quantifies modality reliability via self-supervised aleatoric uncertainty. This mechanism explicitly guides expert routing, enabling the model to suppress error propagation from unreliable signals while preserving task-relevant information. Extensive experiments indicate that QA-MoE achieves competitive or state-of-the-art performance across diverse degradation scenarios and exhibits a promising One-Checkpoint-for-All property in practice.},
	booktitle = {Proceedings of the 64th {Annual} {Meeting} of the {Association} for {Computational} {Linguistics} ({Volume} 1: {Long} {Papers})},
	publisher = {Association for Computational Linguistics},
	author = {Zhu, Yitong and Jiang, Yuxuan and Jiang, Guanxuan and Hou, Bojing and Zhou, Peng Yuan and Lin, Ge and Wang, Yuyang},
	editor = {Liakata, Maria and Moreira, Viviane P. and Zhang, Jiajun and Jurgens, David},
	month = jul,
	year = {2026},
	pages = {31689--31703},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021