analiza aiqbench
This research introduces the Integrated Imputation and Classification Network (IICN), a novel architecture that jointly optimizes missing data estimation and supervised classification to achieve Bayes-optimal performance. By adversarially training an imputer alongside a discriminator, the method outperforms traditional decoupled pipelines on standard benchmarks like FashionMNIST and CIFAR-10. The work advances fundamental machine learning theory by proving that this integrated approach effectively marginalizes over missing coordinates without relying on external generative models.
Integrated Imputation-Classification for Supervised Learning with Missing Data
arXiv:2610.04273v1 Announce Type: new Abstract: We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-classdiscriminator adversarially with a single class supervised classification objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed" class. We prove that at the global optimum, the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings.
Abstract:We study supervised classification problems with missing feature values. Existing approaches often decouple imputation from classification, producing imputations that may be plausible but uninformative for prediction. Instead, we propose the Integrated Imputation and Classification Network (IICN), which jointly trains an imputer and an ${(n{+}1)}$-classdiscriminator adversarially with a single class supervised classification objective, where the discriminator learns to distinguish among the $n$ true classes and an additional ``imputed" class. We prove that at the global optimum, the imputer and discriminator together implement marginalization over missing coordinates and yield a Bayes-optimal classifier. We evaluate IICN on FashionMNIST, CIFAR-10, and tabular datasets with naturally occurring missingness. IICN outperforms classical impute-then-classify pipelines and recent generative baselines, showing strong robustness and accuracy in challenging settings.
Machine Learning (cs.LG)
arXiv:2610.04273 [cs.LG]
(or arXiv:2610.04273v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.04273 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 214 cuvinte
Subiecte conexe
SensorFM: Towards a general intelligence and interface for wearable health data
Google Research · 9 iul. 2026
Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Microsoft Research · 11 aug. 2026
Unsupervised Learning for Missing Modalities in Multimodal Learning
arXiv · 16 iun. 2026
Design Choices for Multimodal Transformer Learning with Missing and Longitudinal Healthcare Data
arXiv · 14 oct. 2026