Problem
Research questions and friction points this paper is trying to address.
Multimodal Sentiment Analysis
modality imbalance
optimization-based methods
discriminative contribution
The Illusion of Balanced Multimodal Sentiment Analysis: Beyond the Limits of Optimization-Based Methods
🤖 AI Summary
本文针对多模态情感分析中的模态不平衡问题，通过统一评估框架和理论诊断方法失效原因，并提出基于保留性能的模态价值评估研究议程。
📝 Abstract
Multimodal Sentiment Analysis (MSA) remains constrained by modality imbalance, yet the field continues to rely on optimization-based balancing methods that promise more than they deliver. We provide three contributions: 1) a unified evaluation framework testing gradient and loss-based balancing strategies under controlled settings; 2) a theoretical diagnosis explaining why these methods fail, as they conflate fitting speed with discriminative contribution; and 3) a research agenda toward held-out discriminative modality valuation. Experiments on CMU-MOSI and CMU-MOSEI reveal three shortcomings: no strategy reliably outperforms Late Concatenation; performance is sensitive to hyperparameters; and even ratio calibration fails to yield consistent gains. The core issue is fundamental: loss is not utility, and gradients are not importance. Modality imbalance remains unresolved, motivating utility estimation from held-out performance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Unified Evaluation Framework
Gradient and Loss-based Balancing Strategies
Held-out Discriminative Modality Valuation
🔎 Similar Papers
No similar papers found.
