Triple Disentangled Representation Learning for Multimodal Affective Analysis
This work addresses a specific bottleneck in multimodal affective analysis by improving representation learning, though it is incremental as it builds on existing disentanglement methods.
The paper tackles the problem of irrelevant or conflicting information in modality-specific representations for multimodal affective analysis by proposing TriDiRA, a triple disentanglement approach that separates modality-invariant, effective modality-specific, and ineffective modality-specific representations, resulting in outperforming state-of-the-art methods on four benchmark datasets.
Multimodal learning has exhibited a significant advantage in affective analysis tasks owing to the comprehensive information of various modalities, particularly the complementary information. Thus, many emerging studies focus on disentangling the modality-invariant and modality-specific representations from input data and then fusing them for prediction. However, our study shows that modality-specific representations may contain information that is irrelevant or conflicting with the tasks, which downgrades the effectiveness of learned multimodal representations. We revisit the disentanglement issue, and propose a novel triple disentanglement approach, TriDiRA, which disentangles the modality-invariant, effective modality-specific and ineffective modality-specific representations from input data. By fusing only the modality-invariant and effective modality-specific representations, TriDiRA can significantly alleviate the impact of irrelevant and conflicting information across modalities during model training. Extensive experiments conducted on four benchmark datasets demonstrate the effectiveness and generalization of our triple disentanglement, which outperforms SOTA methods.