Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits
This work addresses the challenge of handling unreliable data sources in multi-modal learning, though it appears incremental as it builds on existing fusion techniques with a focus on credibility assessment.
The paper tackled the problem of late multi-modal fusion in noisy, multi-source domains by proposing a credibility-aware method using probabilistic circuits, which reliably inferred modality credibility while maintaining competitive performance with state-of-the-art approaches.
We consider the problem of late multi-modal fusion for discriminative learning. Motivated by noisy, multi-source domains that require understanding the reliability of each data source, we explore the notion of credibility in the context of multi-modal fusion. We propose a combination function that uses probabilistic circuits (PCs) to combine predictive distributions over individual modalities. We also define a probabilistic measure to evaluate the credibility of each modality via inference queries over the PC. Our experimental evaluation demonstrates that our fusion method can reliably infer credibility while maintaining competitive performance with the state-of-the-art.