@inproceedings{lin-etal-2025-t2dr,
    title = "$T^2DR$: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learning",
    author = "Lin, Han  and
      Tang, Xiu  and
      Li, Huan  and
      Cao, Wenxue  and
      Wu, Sai  and
      Yao, Chang  and
      Shou, Lidan  and
      Chen, Gang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.452/",
    pages = "8602--8616",
    ISBN = "979-8-89176-256-5",
    abstract = "Multimodal learning is garnering significant attention for its capacity to represent diverse human perceptions (e.g., linguistic, acoustic, and visual signals), achieving more natural and intuitive interactions with technology.However, the frequent occurrence of incomplete data, either within a single modality (intra-modality) or across different modalities (inter-modality), presents substantial challenges in reliable semantic interpretation and model reasoning.Furthermore, there is currently no robust representation learning mechanism capable of managing both intra-modality and inter-modality real-data deficiencies.To address this challenge, we present $\text{T}^2$DR, a two-tier deficiency-resistant framework for incomplete multimodal learning, which comprises two main modules:(1) Intra-Modal Deficiency-Resistant module (IADR): To address fine-grained deficiencies, we introduce Intra-Attn to focus on the available data while avoiding excessive suppression of the missing regions.(2) Inter-Modal Deficiency-Resistant module (IEDR): To handle coarse-grained deficiencies, we propose the shared feature prediction (SFP) to leverage cross-modal shared features for preliminary data imputation. Subsequently, we apply Inter-Attn to allocate appropriate attention to each modality based on the results from the capability-aware scorer (CAS).Extensive experiments are performed on two well-known multimodal benchmarks, CMU-MOSI and CMU-MOSEI, across various missing scenarios for sentiment analysis. Experimental results show that $\text{T}^2$DR significantly outperforms the SOTA models. Code is available at \url{https://github.com/LH019/T2DR}."
}