# GAUGE: Granularity-Adaptive Counterfactual Gating of Evidence for Incomplete Multimodal Classification

arXiv: https://arxiv.org/abs/2608.05608 · HTML: https://mlsanity.com/paper/2608.05608/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 6 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [SMIL: Multimodal Learning with Severely Missing Modality](https://mlsanity.com/paper/2103.05677/) (2021)
- [Are Multimodal Transformers Robust to Missing Modality?](https://mlsanity.com/paper/2204.05454/) (2022)
- [Multimodal Prompting with Missing Modalities for Visual Recognition](https://mlsanity.com/paper/2303.03369/) (2023)
- [Generalized Multimodal ELBO](https://mlsanity.com/paper/2105.02470/) (2021)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [M3Care: Learning with Missing Modalities in Multimodal Healthcare Data](https://mlsanity.com/paper/2210.17292/) (2022)
- [Towards Good Practices for Missing Modality Robust Action Recognition](https://mlsanity.com/paper/2211.13916/) (2022)
- [DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency](https://mlsanity.com/paper/2403.06197/) (2024)
- [TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data](https://mlsanity.com/paper/2407.07582/) (2024)
- [Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards](https://mlsanity.com/paper/2405.13459/) (2024)
- [RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates](https://mlsanity.com/paper/2312.10386/) (2023)
- [Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusion](https://mlsanity.com/paper/2503.19776/) (2025)
- [A Unified Taylor Framework for Revisiting Attribution Methods](https://mlsanity.com/paper/2008.09695/) (2020)
- [Gradient-Guided Modality Decoupling for Missing-Modality Robustness](https://mlsanity.com/paper/2402.16318/) (2024)
- [Synergistic Prompting for Robust Visual Recognition with Missing Modalities](https://mlsanity.com/paper/2507.07802/) (2025)
- [Incomplete Modality Disentangled Representation for Ophthalmic Disease Grading and Diagnosis](https://mlsanity.com/paper/2502.11724/) (2025)
- [Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation](https://mlsanity.com/paper/2507.19882/) (2025)
- [Enhancing Interpretability for Vision Models via Shapley Value Optimization](https://mlsanity.com/paper/2512.14354/) (2025)

## Abstract (arXiv)

Multimodal classification typically assumes all modalities are available, yet real-world inputs are often incomplete. Imputation and dynamic fusion can mitigate such incompleteness, but existing methods operate at a coarse modality level and thus cannot retain reliable components while suppressing misleading ones within the same recovered modality, compromising prediction reliability. To address this issue, we propose GAUGE, a lightweight counterfactual gating framework for incomplete multimodal classification. GAUGE first imputes missing modalities with a frozen imputer and encodes observed and recovered inputs uniformly as fine-grained evidence units. Rather than intervening on each unit explicitly, GAUGE scores the counterfactual effect of replacing every unit with a reference representation through prediction-aware Taylor evidence scores, all obtained in a single forward-backward pass. These scores are mapped to continuous gates, which are converted into additive attention-logit biases for unit-wise evidence modulation without altering the backbone architecture. Experiments across six benchmarks demonstrate that GAUGE outperforms strong baselines across diverse incomplete-input settings. Furthermore, a Taylor remainder theoretical analysis characterizes the error of the first-order approximation relative to the exact counterfactual effect, establishing GAUGE as a principled and scalable framework for fine-grained evidence control under modality incompleteness.