# Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits

arXiv: https://arxiv.org/abs/2403.03281 · HTML: https://mlsanity.com/paper/2403.03281/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [MMTM: Multimodal Transfer Module for CNN Fusion](https://mlsanity.com/paper/1911.08670/) (2019)
- [Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits](https://mlsanity.com/paper/2004.06231/) (2020)
- [Trusted Multi-View Classification](https://mlsanity.com/paper/2102.02051/) (2021)
- [CentralNet: a Multilayer Approach for Multimodal Fusion](https://mlsanity.com/paper/1808.07275/) (2018)
- [MFAS: Multimodal Fusion Architecture Search](https://mlsanity.com/paper/1903.06496/) (2019)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Strudel: Learning Structured-Decomposable Probabilistic Circuits](https://mlsanity.com/paper/2007.09331/) (2020)
- [UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation](https://mlsanity.com/paper/1911.05611/) (2019)
- [Building Expressive and Tractable Probabilistic Generative Models: A Review](https://mlsanity.com/paper/2402.00759/) (2024)
- [A New Look at Causal Independence](https://mlsanity.com/paper/1302.6814/) (2013)

## Built on by (most cited first, 5 of 5)

- [Tractable Representation Learning with Probabilistic Circuits](https://mlsanity.com/paper/2507.04385/) (2025)
- [Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameters](https://mlsanity.com/paper/2507.07941/) (2025)
- [Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits](https://mlsanity.com/paper/2603.26629/) (2026)
- [Geometry-Aware Probabilistic Circuits via Voronoi Tessellations](https://mlsanity.com/paper/2603.11946/) (2026)
- [Reliable Fusion of Conflicting Experts](https://mlsanity.com/paper/2609.27913/) (2026)

## Abstract (arXiv)

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.