Conformal Prediction for Multimodal Regression (2410.19653v2)
Abstract: This paper introduces multimodal conformal regression. Traditionally confined to scenarios with solely numerical input features, conformal prediction is now extended to multimodal contexts through our methodology, which harnesses internal features from complex neural network architectures processing images and unstructured text. Our findings highlight the potential for internal neural network features, extracted from convergence points where multimodal information is combined, to be used by conformal prediction to construct prediction intervals (PIs). This capability paves new paths for deploying conformal prediction in domains abundant with multimodal data, enabling a broader range of problems to benefit from guaranteed distribution-free uncertainty quantification.
- A gentle introduction to conformal prediction and distribution-free uncertainty quantification. arXiv preprint arXiv:2107.07511, 2021.
- Image-to-image regression with distribution-free uncertainty quantification and applications in imaging. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato, editors, Proceedings of the 39th International Conference on Machine Learning, volume 162 of Proceedings of Machine Learning Research, pages 717–730. PMLR, 17–23 Jul 2022. URL https://proceedings.mlr.press/v162/angelopoulos22a.html.
- APRUM. Homage - asok bose. URL https://www.aprum.umontreal.ca/Lettres/L06/060131.htm#AsokBose. Accessed: 2024-10-15.
- Target strangeness: A novel conformal prediction difficulty estimator. arXiv preprint arXiv:XXXX.YYYYY, 2024.
- Amitava Bose. Author profile - scopus. https://www.scopus.com/authid/detail.uri?authorId=35609793000, a. Accessed: 2024-10-11.
- Asok K. Bose. Author profile - scopus. https://www.scopus.com/authid/detail.uri?authorId=22974160400, b. Accessed: 2024-10-11.
- Henrik Boström. crepes: a python package for generating conformal regressors and predictive systems. In Ulf Johansson, Henrik Boström, Khuong An Nguyen, Zhiyuan Luo, and Lars Carlsson, editors, Proceedings of the Eleventh Symposium on Conformal and Probabilistic Prediction and Applications, volume 179 of Proceedings of Machine Learning Research. PMLR, 2022. https://github.com/henrikbostrom/crepes, Accessed: February, 2024, License: https://github.com/henrikbostrom/crepes?tab=BSD-3-Clause-1-ov-file.
- A package for learning on tabular and text data with transformers. In Proceedings of the Third Workshop on Multimodal Artificial Intelligence, pages 69–73, Mexico City, Mexico, June 2021. Association for Computational Linguistics. doi: 10.18653/v1/2021.maiworkshop-1.10. URL https://www.aclweb.org/anthology/2021.maiworkshop-1.10. https://github.com/georgian-io/Multimodal-Toolkit, Accessed: April, 2024, License: https://github.com/georgian-io/Multimodal-Toolkit/blob/master/LICENSE.
- Conformal prediction via regression-as-classification. In NeurIPS 2023 Workshop on Regulatable ML, 2023. URL https://openreview.net/forum?id=eKrYMGpXVY.
- Deep learning for path loss prediction at 7 ghz in urban environment. IEEE Access, 11:33498–33508, 2023.
- Inductive confidence machines for regression. In Machine learning: ECML 2002: 13th European conference on machine learning Helsinki, Finland, August 19–23, 2002 proceedings 13, pages 345–356. Springer, 2002.
- Model-aided Deep Learning Method for Path Loss Prediction in Mobile Communication Systems at 2.6 GHz. IEEE Access, January 2020. https://github.com/jakthra/PathLossPredictionSatelliteImages, Accessed: September, 2023,test, License: https://github.com/jakthra/PathLossPredictionSatelliteImages?tab=MIT-1-ov-file.
- Computationally efficient versions of conformal predictive distributions. Neurocomputing, 397:292–308, 2020.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
