{"type":"ScholarlyArticle","title":"Decoupling and Reconstructing: A Multimodal Sentiment Analysis Framework Towards Robustness","authors":[{"name":"Mingzheng Yang","slug":"mingzheng-yang","given":"Mingzheng","family":"Yang","affiliation":""},{"name":"Kai Zhang","slug":"kai-zhang","given":"Kai","family":"Zhang","affiliation":""},{"name":"Yuyang Ye","slug":"yuyang-ye","given":"Yuyang","family":"Ye","affiliation":""},{"name":"Yanghai Zhang","slug":"yanghai-zhang","given":"Yanghai","family":"Zhang","affiliation":""},{"name":"Runlong Yu","slug":"runlong-yu","given":"Runlong","family":"Yu","affiliation":""},{"name":"Min Hou","slug":"min-hou","given":"Min","family":"Hou","affiliation":""}],"abstract":"Multimodal sentiment analysis (MSA) has shown promising results but often poses significant challenges in real-world applications due to its dependence on the complete and aligned multimodal sequences. While existing approaches attempt to address missing modalities through feature reconstruction, they often neglect the complex interplay between homogeneous and heterogeneous relationships in multimodal features. To address this problem, we propose Decoupled-Adaptive Reconstruction (DAR), a novel framework that explicitly addresses these limitations through two key components: (1) a mutual information-based decoupling module that decomposes features into common and independent representations, and (2) a reconstruction module that independently processes these decoupled features before fusion for downstream tasks. Extensive experiments on two benchmark datasets demonstrate that DAR significantly outperforms existing methods in both modality reconstruction and sentiment analysis tasks, particularly in scenarios with missing or unaligned modalities. Our results show improvements of 2.21% in bi-classification accuracy and 3.9% in regression error compared to state-of-the-art baselines on the MOSEI dataset.","doi":"10.24963/ijcai.2025/757","url":"https://ijcai.org/proceedings/2025/757","pdf":"https://ijcai.org/proceedings/2025/0757.pdf","markdown":"https://ijcai.org/proceedings/2025/757.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/757","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":757,"pages":{"first":6803,"last":6811},"keywords":["Machine Learning: ML: Multi-modal learning","Natural Language Processing: NLP: Sentiment analysis, stylistic analysis, and argument mining","Machine Learning: ML: Robustness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}