mlsanityData to 14 Oct 2026

ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data

arXiv 2306.12330 ↗First posted 21 Jun 2023cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Tabular biomedical data poses challenges in machine learning because it is often high-dimensional and typically low-sample-size (HDLSS). Previous research has attempted to address these challenges via local feature selection, but existing approaches often fail to achieve optimal performance due to their limitation in identifying globally important features and their susceptibility to the co-adaptation problem. In this paper, we propose ProtoGate, a prototype-based neural model for feature selection on HDLSS data. ProtoGate first selects instance-wise features via adaptively balancing global and local feature selection. Furthermore, ProtoGate employs a non-parametric prototype-based prediction mechanism to tackle the co-adaptation problem, ensuring the feature selection results and predictions are consistent with underlying data clusters. We conduct comprehensive experiments to evaluate the performance and interpretability of ProtoGate on synthetic and real-world datasets. The results show that ProtoGate generally outperforms state-of-the-art methods in prediction accuracy by a clear margin while providing high-fidelity feature selection and explainable predictions. Code is available at https://github.com/SilenceX12138/ProtoGate.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 34 of its 83 references that are in the map. First posted on arXiv 21 Jun 2023.

Builds on

34 of 83 references.

References · 34

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  8. 2018Sanity Checks for Saliency Mapscited by 1,156
  9. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
  10. 2019TabNet: Attentive Interpretable Tabular Learningcited by 648
  11. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 583
  12. 2021Tabular Data: Deep Learning is Not All You Needcited by 535
22 more
  1. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  2. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
  3. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  4. 2017The Expressive Power of Neural Networks: A View from the Widthcited by 320
  5. 2018AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networkscited by 320
  6. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
  7. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  8. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  9. 2023When Do Neural Nets Outperform Boosted Trees on Tabular Data?cited by 223
  10. 2020Fast Differentiable Sorting and Rankingcited by 197
  11. 2016Discrete Variational Autoencoderscited by 125
  12. 2019Stochastic Optimization of Sorting Networks via Continuous Relaxationscited by 111
  13. 2021Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretationscited by 59
  14. 2022Transfer Learning with Deep Tabular Modelscited by 52
  15. 2021Locally Sparse Neural Networks for Tabular Biomedical Datacited by 34
  16. 2020SoftSeg: Advantages of soft versus binary training for image segmentationcited by 26
  17. 2016Localized Lasso for High-Dimensional Regressioncited by 11
  18. 2022GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Datacited by 6
  19. 2022Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Datacited by 6
  20. 2023The Contextual Lasso: Sparse Linear Models via Deep Neural Networkscited by 6
  21. 2022Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement Learningcited by 5
  22. 2020Neural Generators of Sparse Local Linear Models for Achieving both Accuracy and Interpretabilitycited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 10; 2026: 4.

18 papers.

Sort:

By area:

  1. 2024TALENT: A Tabular Analytics and Learning Toolboxcited by 52
  2. 2025A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilitiescited by 41
  3. 2025TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problemscited by 36
  4. 2025Representation Learning for Tabular Data: A Comprehensive Surveycited by 36
  5. 2024Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Latercited by 30
  6. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  7. 2024TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Modelscited by 16
  8. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  9. 2024TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsettingcited by 5
  10. 2025Self-Explaining Neural Networks for Business Process Monitoringcited by 5
  11. 2025How Well Does Your Tabular Generator Learn the Structure of Tabular Data?cited by 1
  12. 2025Towards Interpretable Deep Neural Networks for Tabular Datacited by 1
6 more
  1. 2026ZAYAN: Disentangled Contrastive Transformer for Tabular Remote Sensing Datacited by 1
  2. 2026DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Datacited by 1
  3. 2025AutoNFS: Automatic Neural Feature Selectioncited by 0
  4. 2025XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoderscited by 0
  5. 2026XSPLAIN: XAI-enabling Splat-based Prototype Learning for Attribute-aware INterpretabilitycited by 0
  6. 2026BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generationcited by 0