i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data

Chen Ma, Wanjie Wang, Shuhao Fan
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:2485-2493, 2026.

Abstract

Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It’s common that only a few features, called the influential features, meaningfully define the clusters. Recovering these influential features is helpful in data interpretation and clustering. We propose i-IF-Learn, an iterative unsupervised framework that jointly performs feature selection and clustering. Our core innovation is an adaptive feature selection statistic that effectively combines pseudo-label supervision with unsupervised signals, dynamically adjusting based on intermediate label reliability to mitigate error propagation common in iterative frameworks. Leveraging low-dimensional embeddings (PCA or Laplacian eigenmaps) followed by $k$-means, i-IF-Learn simultaneously outputs influential feature subset and clustering labels. Numerical experiments on gene microarray and single-cell RNA-seq datasets show that i-IF-Learn significantly surpasses classical and deep clustering baselines. Furthermore, using our selected influential features as preprocessing substantially enhances downstream deep models such as DeepCluster, UMAP, and VAE, highlighting the importance and effectiveness of targeted feature selection.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-ma26a, title = { i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data }, author = {Ma, Chen and Wang, Wanjie and Fan, Shuhao}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {2485--2493}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/ma26a/ma26a.pdf}, url = {https://proceedings.mlr.press/v300/ma26a.html}, abstract = { Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It’s common that only a few features, called the influential features, meaningfully define the clusters. Recovering these influential features is helpful in data interpretation and clustering. We propose i-IF-Learn, an iterative unsupervised framework that jointly performs feature selection and clustering. Our core innovation is an adaptive feature selection statistic that effectively combines pseudo-label supervision with unsupervised signals, dynamically adjusting based on intermediate label reliability to mitigate error propagation common in iterative frameworks. Leveraging low-dimensional embeddings (PCA or Laplacian eigenmaps) followed by $k$-means, i-IF-Learn simultaneously outputs influential feature subset and clustering labels. Numerical experiments on gene microarray and single-cell RNA-seq datasets show that i-IF-Learn significantly surpasses classical and deep clustering baselines. Furthermore, using our selected influential features as preprocessing substantially enhances downstream deep models such as DeepCluster, UMAP, and VAE, highlighting the importance and effectiveness of targeted feature selection. } }
Endnote
%0 Conference Paper %T i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data %A Chen Ma %A Wanjie Wang %A Shuhao Fan %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-ma26a %I PMLR %P 2485--2493 %U https://proceedings.mlr.press/v300/ma26a.html %V 300 %X Unsupervised learning of high-dimensional data is challenging due to irrelevant or noisy features obscuring underlying structures. It’s common that only a few features, called the influential features, meaningfully define the clusters. Recovering these influential features is helpful in data interpretation and clustering. We propose i-IF-Learn, an iterative unsupervised framework that jointly performs feature selection and clustering. Our core innovation is an adaptive feature selection statistic that effectively combines pseudo-label supervision with unsupervised signals, dynamically adjusting based on intermediate label reliability to mitigate error propagation common in iterative frameworks. Leveraging low-dimensional embeddings (PCA or Laplacian eigenmaps) followed by $k$-means, i-IF-Learn simultaneously outputs influential feature subset and clustering labels. Numerical experiments on gene microarray and single-cell RNA-seq datasets show that i-IF-Learn significantly surpasses classical and deep clustering baselines. Furthermore, using our selected influential features as preprocessing substantially enhances downstream deep models such as DeepCluster, UMAP, and VAE, highlighting the importance and effectiveness of targeted feature selection.
APA
Ma, C., Wang, W. & Fan, S.. (2026). i-IF-Learn: Iterative Feature Selection and Unsupervised Learning for High-Dimensional Complex Data . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:2485-2493 Available from https://proceedings.mlr.press/v300/ma26a.html.

Related Material