# Multi-modal Differentiable Unsupervised Feature Selection

arXiv: https://arxiv.org/abs/2303.09381 · HTML: https://mlsanity.com/paper/2303.09381/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 43 references that are in the map.
- First posted on arXiv 16 Mar 2023.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Concrete Autoencoders for Differentiable Feature Selection and Reconstruction](https://mlsanity.com/paper/1901.09346/) (2019)
- [Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding](https://mlsanity.com/paper/1712.09005/) (2017)
- [Error estimates for spectral convergence of the graph Laplacian on random geometric graphs towards the Laplace--Beltrami operator](https://mlsanity.com/paper/1801.10108/) (2018)
- [Locally Sparse Neural Networks for Tabular Biomedical Data](https://mlsanity.com/paper/2106.06468/) (2021)
- [Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation](https://mlsanity.com/paper/2101.09875/) (2021)
- [LOCA: LOcal Conformal Autoencoder for standardized data coordinates](https://mlsanity.com/paper/2004.07234/) (2020)
- [Product Manifold Learning](https://mlsanity.com/paper/2010.09908/) (2020)
- [Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features](https://mlsanity.com/paper/2110.05306/) (2021)
- [Recovering Hidden Components in Multimodal Data with Composite Diffusion Operators](https://mlsanity.com/paper/1808.07312/) (2018)
- [DiSC: Differential Spectral Clustering of Features](https://mlsanity.com/paper/2211.05314/) (2022)
- [ManiFeSt: Manifold-based Feature Selection for Small Data Sets](https://mlsanity.com/paper/2207.08574/) (2022)

## Built on by (most cited first, 5 of 5)

- [FineGates: LLMs Finetuning with Compression using Stochastic Gates](https://mlsanity.com/paper/2412.12951/) (2024)
- [Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity](https://mlsanity.com/paper/2602.09169/) (2026)
- [Spectral Self-supervised Feature Selection](https://mlsanity.com/paper/2407.09061/) (2024)
- [Generalizable and Robust Spectral Method for Multi-view Representation Learning](https://mlsanity.com/paper/2411.02138/) (2024)
- [Uncovering a Winning Lottery Ticket with Continuously Relaxed Bernoulli Gates](https://mlsanity.com/paper/2603.08914/) (2026)

## Abstract (arXiv)

Multi-modal high throughput biological data presents a great scientific opportunity and a significant computational challenge. In multi-modal measurements, every sample is observed simultaneously by two or more sets of sensors. In such settings, many observed variables in both modalities are often nuisance and do not carry information about the phenomenon of interest. Here, we propose a multi-modal unsupervised feature selection framework: identifying informative variables based on coupled high-dimensional measurements. Our method is designed to identify features associated with two types of latent low-dimensional structures: (i) shared structures that govern the observations in both modalities and (ii) differential structures that appear in only one modality. To that end, we propose two Laplacian-based scoring operators. We incorporate the scores with differentiable gates that mask nuisance features and enhance the accuracy of the structure captured by the graph Laplacian. The performance of the new scheme is illustrated using synthetic and real datasets, including an extended biological application to single-cell multi-omics.