# Context-specific Credibility-aware Multimodal Fusion with Conditional Probabilistic Circuits

arXiv: https://arxiv.org/abs/2603.26629 · HTML: https://mlsanity.com/paper/2603.26629/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [MMTM: Multimodal Transfer Module for CNN Fusion](https://mlsanity.com/paper/1911.08670/) (2019)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [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)
- [Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions](https://mlsanity.com/paper/2111.08456/) (2021)
- [Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures](https://mlsanity.com/paper/1905.08550/) (2019)
- [Interventional Sum-Product Networks: Causal Inference with Tractable Probabilistic Models](https://mlsanity.com/paper/2102.10440/) (2021)
- [UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation](https://mlsanity.com/paper/1911.05611/) (2019)
- [HyperSPNs: Compact and Expressive Probabilistic Circuits](https://mlsanity.com/paper/2112.00914/) (2021)
- [Building Expressive and Tractable Probabilistic Generative Models: A Review](https://mlsanity.com/paper/2402.00759/) (2024)
- [Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits](https://mlsanity.com/paper/2403.03281/) (2024)
- [Tractable Representation Learning with Probabilistic Circuits](https://mlsanity.com/paper/2507.04385/) (2025)
- [chiSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains](https://mlsanity.com/paper/2408.07545/) (2024)

## Built on by (most cited first, 2 of 2)

- [Reliable Fusion of Conflicting Experts](https://mlsanity.com/paper/2609.27913/) (2026)
- [Controlled Acquisition and Abstention in Three-Channel Score Conflicts](https://mlsanity.com/paper/2610.10808/) (2026)

## Abstract (arXiv)

Multimodal fusion requires integrating information from multiple sources that may conflict depending on context. Existing fusion approaches typically rely on static assumptions about source reliability, limiting their ability to resolve conflicts when a modality becomes unreliable due to situational factors such as sensor degradation or class-specific corruption. We introduce C2MF, a context-specfic credibility-aware multimodal fusion framework that models per-instance source reliability using a Conditional Probabilistic Circuit (CPC). We formalize instance-level reliability through Context-Specific Information Credibility (CSIC), a KL-divergence-based measure computed exactly from the CPC. CSIC generalizes conventional static credibility estimates as a special case, enabling principled and adaptive reliability assessment. To evaluate robustness under cross-modal conflicts, we propose the Conflict benchmark, in which class-specific corruptions deliberately induce discrepancies between different modalities. Experimental results show that C2MF improves predictive accuracy by up to 29% over static-reliability baselines in high-noise settings, while preserving the interpretability advantages of probabilistic circuit-based fusion.