The Illusion of Balanced Multimodal Sentiment Analysis: Beyond the Limits of Optimization-Based Methods
Read the original on arXiv Computation and Language →The paper critiques current optimization-based methods for balancing modalities in Multimodal Sentiment Analysis, arguing they overpromise and underdeliver. It introduces a unified evaluation framework that tests gradient- and loss-based balancing strategies, provides a theoretical diagnosis showing these methods conflate fitting speed with discriminative contribution, and proposes a research agenda for held‑out discriminative modality valuation. Experiments on CMU‑MOSI and CMU‑MOSEI demonstrate that no strategy consistently outperforms Late Concatenation, performance is highly sensitive to hyperparameters, and ratio calibration does not yield reliable gains, highlighting that loss is not utility and gradients are not importance.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.