# Locally Sparse Neural Networks for Tabular Biomedical Data

arXiv: https://arxiv.org/abs/2106.06468 · HTML: https://mlsanity.com/paper/2106.06468/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 72 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 30 of 34)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [The Implicit Bias of Gradient Descent on Separable Data](https://mlsanity.com/paper/1710.10345/) (2017)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Tabular Data: Deep Learning is Not All You Need](https://mlsanity.com/paper/2106.03253/) (2021)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [Understanding Deep Neural Networks with Rectified Linear Units](https://mlsanity.com/paper/1611.01491/) (2016)
- [Learning to Explain: An Information-Theoretic Perspective on Model Interpretation](https://mlsanity.com/paper/1802.07814/) (2018)
- [Real Time Image Saliency for Black Box Classifiers](https://mlsanity.com/paper/1705.07857/) (2017)
- [Dynamic Channel Pruning: Feature Boosting and Suppression](https://mlsanity.com/paper/1810.05331/) (2018)
- [CXPlain: Causal Explanations for Model Interpretation under Uncertainty](https://mlsanity.com/paper/1910.12336/) (2019)
- [Concrete Autoencoders for Differentiable Feature Selection and Reconstruction](https://mlsanity.com/paper/1901.09346/) (2019)
- [Group Sparse Regularization for Deep Neural Networks](https://mlsanity.com/paper/1607.00485/) (2016)
- [REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models](https://mlsanity.com/paper/1703.07370/) (2017)
- [More is Less: A More Complicated Network with Less Inference Complexity](https://mlsanity.com/paper/1703.08651/) (2017)

## Built on by (most cited first, 30 of 34)

- [Transfer Learning with Deep Tabular Models](https://mlsanity.com/paper/2206.15306/) (2022)
- [Representation Learning for Tabular Data: A Comprehensive Survey](https://mlsanity.com/paper/2504.16109/) (2025)
- [Explaining Time Series via Contrastive and Locally Sparse Perturbations](https://mlsanity.com/paper/2401.08552/) (2024)
- [Interpretable Deep Clustering for Tabular Data](https://mlsanity.com/paper/2306.04785/) (2023)
- [ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data](https://mlsanity.com/paper/2306.12330/) (2023)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields](https://mlsanity.com/paper/2505.18125/) (2025)
- [Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck](https://mlsanity.com/paper/2309.03800/) (2023)
- [Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons](https://mlsanity.com/paper/2502.03391/) (2025)
- [ICR-RL: Deep Reinforcement Learning via In-Context Regression](https://mlsanity.com/paper/2509.11259/) (2025)
- [Contextual Feature Selection with Conditional Stochastic Gates](https://mlsanity.com/paper/2312.14254/) (2023)
- [GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data](https://mlsanity.com/paper/2211.06302/) (2022)
- [Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data](https://mlsanity.com/paper/2211.15616/) (2022)
- [The Contextual Lasso: Sparse Linear Models via Deep Neural Networks](https://mlsanity.com/paper/2302.00878/) (2023)
- [Multi-modal Differentiable Unsupervised Feature Selection](https://mlsanity.com/paper/2303.09381/) (2023)
- [Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings](https://mlsanity.com/paper/2511.06961/) (2025)
- [Optimizing model-agnostic Random Subspace ensembles](https://mlsanity.com/paper/2109.03099/) (2021)
- [Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs](https://mlsanity.com/paper/2407.09790/) (2024)
- [ManiFeSt: Manifold-based Feature Selection for Small Data Sets](https://mlsanity.com/paper/2207.08574/) (2022)
- [Efficient Verification-Based Face Identification](https://mlsanity.com/paper/2312.13240/) (2023)
- [DAGnosis: Localized Identification of Data Inconsistencies using Structures](https://mlsanity.com/paper/2402.17599/) (2024)
- [Sparse Binarization for Fast Keyword Spotting](https://mlsanity.com/paper/2406.06634/) (2024)
- [Leveraging Machine Learning Models to Predict the Outcome of Digital Medical Triage Interviews](https://mlsanity.com/paper/2504.11977/) (2025)
- [Distributionally Robust Feature Selection](https://mlsanity.com/paper/2510.21113/) (2025)
- [DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data](https://mlsanity.com/paper/2605.03430/) (2026)
- [Neuronal Cell Type Classification using Deep Learning](https://mlsanity.com/paper/2306.00528/) (2023)
- [Learning Locally Interpretable Rule Ensemble](https://mlsanity.com/paper/2306.11481/) (2023)
- [Interpretable classifiers for tabular data via discretization and feature selection](https://mlsanity.com/paper/2402.05680/) (2024)
- [Conditional Deep Canonical Time Warping](https://mlsanity.com/paper/2412.18234/) (2024)
- [AutoNFS: Automatic Neural Feature Selection](https://mlsanity.com/paper/2503.13304/) (2025)

## Abstract (arXiv)

Tabular datasets with low-sample-size or many variables are prevalent in biomedicine. Practitioners in this domain prefer linear or tree-based models over neural networks since the latter are harder to interpret and tend to overfit when applied to tabular datasets. To address these neural networks' shortcomings, we propose an intrinsically interpretable network for heterogeneous biomedical data. We design a locally sparse neural network where the local sparsity is learned to identify the subset of most relevant features for each sample. This sample-specific sparsity is predicted via a textitgating network, which is trained in tandem with the textitprediction network. By forcing the model to select a subset of the most informative features for each sample, we reduce model overfitting in low-sample-size data and obtain an interpretable model. We demonstrate that our method outperforms state-of-the-art models when applied to synthetic or real-world biomedical datasets using extensive experiments. Furthermore, the proposed framework dramatically outperforms existing schemes when evaluating its interpretability capabilities. Finally, we demonstrate the applicability of our model to two important biomedical tasks: survival analysis and marker gene identification.