analiza aiqbench
This research introduces Missing-by-Design (MBD), a framework enabling the selective revocation of specific data modalities in multimodal sentiment analysis systems. By utilizing generator-based reconstruction and certifiable parameter modifications, it offers an efficient "surgical unlearning" method that preserves predictive performance while ensuring privacy compliance without full model retraining.
Missing-by-Design: Certifiable Modality Deletion for Revocable Multimodal Sentiment Analysis
arXiv:2602.16144v4 Announce Type: replace Abstract: As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for revocable multimodal sentiment analysis that combines structured representation learning with a certifiable parameter-modification pipeline. Revocability is critical in privacy-sensitive applications where users or regulators may request removal of modality-specific information. MBD learns property-aware embeddings and employs generator-based reconstruction to recover missing channels while preserving task-relevant signals. For deletion requests, the framework applies saliency-driven candidate selection and a calibrated Gaussian update to produce a machine-verifiable Modality Deletion Certificate. Experiments on benchmark datasets show that MBD achieves strong predictive performance under incomplete inputs and delivers a practical privacy-utility trade-off, positioning surgical unlearning as an efficient alternative to full retraining.
Abstract:As multimodal systems increasingly process sensitive personal data, the ability to selectively revoke specific data modalities has become a critical requirement for privacy compliance and user autonomy. We present Missing-by-Design (MBD), a unified framework for revocable multimodal sentiment analysis that combines structured representation learning with a certifiable parameter-modification pipeline. Revocability is critical in privacy-sensitive applications where users or regulators may request removal of modality-specific information. MBD learns property-aware embeddings and employs generator-based reconstruction to recover missing channels while preserving task-relevant signals. For deletion requests, the framework applies saliency-driven candidate selection and a calibrated Gaussian update to produce a machine-verifiable Modality Deletion Certificate. Experiments on benchmark datasets show that MBD achieves strong predictive performance under incomplete inputs and delivers a practical privacy-utility trade-off, positioning surgical unlearning as an efficient alternative to full retraining.
21 pages, 6 figures. In the previous version, Juntendo University was erroneously listed as the affiliation; we must clarify that this paper has absolutely no relation to Juntendo University. Therefore, we have replaced this affiliation in the new version
Computation and Language (cs.CL); Machine Learning (cs.LG)
arXiv:2602.16144 [cs.CL]
(or arXiv:2602.16144v4 [cs.CL] for this version)
Text integral sub licența deschisă a publicației · 186 cuvinte
Subiecte conexe
Reliability-aware Cross-sample Enhancement for Robust Multimodal Sentiment Analysis
arXiv · 28 sept. 2026
SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data
arXiv · 25 sept. 2026
Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
arXiv · 5 aug. 2026
Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?
arXiv · 21 iul. 2026