Search papers, labs, and topics across Lattice.
This paper introduces GAUGE, a novel counterfactual gating framework designed to enhance multimodal classification in scenarios where input modalities are incomplete. By employing a frozen imputer and scoring the counterfactual effects of evidence units through prediction-aware Taylor evidence scores, GAUGE effectively modulates evidence without compromising the backbone architecture. Experimental results across six benchmarks reveal that GAUGE consistently outperforms existing methods, demonstrating its robustness in handling incomplete inputs while maintaining prediction reliability.
GAUGE achieves superior multimodal classification by fine-tuning evidence modulation at a granular level, even when faced with incomplete data inputs.
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.
