Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?
Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every missing modality be repaired?} A per-sample oracle analysis shows the answer is not always: full-modality input is optimal for only a small fraction of samples, and every modality subset is preferred by some samples. These results suggest that adding or repairing modalities may not always improve prediction, and that the utility of each modality is sample-dependent. Building on this finding, we propose \textbf{S}ufficie
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%mangiucugna/json_repair →
“Fuzzy title match (0.73): “Should Missing Modalities Always Be Necessary to Repair for ” ≈ “mangiucugna/json_repair””
- LinkedLinked via arxiv author · 85%Yubo Gao →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Haotian Wu →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Xiaoyu Xu →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Yibo Yan →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Yaohong Chen →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Ruoshui Peng →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”
- LinkedLinked via arxiv author · 85%Fei Pan →
“Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?”