Feature Shift Localization Network

Mı́riam Barrabés, Daniel Mas Montserrat, Kapal Dev, Alexander G. Ioannidis
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:3003-3029, 2025.

Abstract

Feature shifts between data sources are present in many applications involving healthcare, biomedical, socioeconomic, financial, survey, and multi-sensor data, among others, where unharmonized heterogeneous data sources, noisy data measurements, or inconsistent processing and standardization pipelines can lead to erroneous features. Localizing shifted features is important to address the underlying cause of the shift and correct or filter the data to avoid degrading downstream analysis. While many techniques can detect distribution shifts, localizing the features originating them is still challenging, with current solutions being either inaccurate or not scalable to large and high-dimensional datasets. In this work, we introduce the Feature Shift Localization Network (FSL-Net), a neural network that can localize feature shifts in large and high-dimensional datasets in a fast and accurate manner. The network, trained with a large number of datasets, learns to extract the statistical properties of the datasets and can localize feature shifts from previously unseen datasets and shifts without the need for re-training. The code and ready-to-use trained model are available at https://github.com/AI-sandbox/FSL-Net.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-barrabes25a, title = {Feature Shift Localization Network}, author = {Barrab\'{e}s, M\'{\i}riam and Mas Montserrat, Daniel and Dev, Kapal and Ioannidis, Alexander G.}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {3003--3029}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/barrabes25a/barrabes25a.pdf}, url = {https://proceedings.mlr.press/v267/barrabes25a.html}, abstract = {Feature shifts between data sources are present in many applications involving healthcare, biomedical, socioeconomic, financial, survey, and multi-sensor data, among others, where unharmonized heterogeneous data sources, noisy data measurements, or inconsistent processing and standardization pipelines can lead to erroneous features. Localizing shifted features is important to address the underlying cause of the shift and correct or filter the data to avoid degrading downstream analysis. While many techniques can detect distribution shifts, localizing the features originating them is still challenging, with current solutions being either inaccurate or not scalable to large and high-dimensional datasets. In this work, we introduce the Feature Shift Localization Network (FSL-Net), a neural network that can localize feature shifts in large and high-dimensional datasets in a fast and accurate manner. The network, trained with a large number of datasets, learns to extract the statistical properties of the datasets and can localize feature shifts from previously unseen datasets and shifts without the need for re-training. The code and ready-to-use trained model are available at https://github.com/AI-sandbox/FSL-Net.} }
Endnote
%0 Conference Paper %T Feature Shift Localization Network %A Mı́riam Barrabés %A Daniel Mas Montserrat %A Kapal Dev %A Alexander G. Ioannidis %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-barrabes25a %I PMLR %P 3003--3029 %U https://proceedings.mlr.press/v267/barrabes25a.html %V 267 %X Feature shifts between data sources are present in many applications involving healthcare, biomedical, socioeconomic, financial, survey, and multi-sensor data, among others, where unharmonized heterogeneous data sources, noisy data measurements, or inconsistent processing and standardization pipelines can lead to erroneous features. Localizing shifted features is important to address the underlying cause of the shift and correct or filter the data to avoid degrading downstream analysis. While many techniques can detect distribution shifts, localizing the features originating them is still challenging, with current solutions being either inaccurate or not scalable to large and high-dimensional datasets. In this work, we introduce the Feature Shift Localization Network (FSL-Net), a neural network that can localize feature shifts in large and high-dimensional datasets in a fast and accurate manner. The network, trained with a large number of datasets, learns to extract the statistical properties of the datasets and can localize feature shifts from previously unseen datasets and shifts without the need for re-training. The code and ready-to-use trained model are available at https://github.com/AI-sandbox/FSL-Net.
APA
Barrabés, M., Mas Montserrat, D., Dev, K. & Ioannidis, A.G.. (2025). Feature Shift Localization Network. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:3003-3029 Available from https://proceedings.mlr.press/v267/barrabes25a.html.

Related Material