mlsanityData to 7 Oct 2026

SHAPNN: Shapley Value Regularized Tabular Neural Network

arXiv 2309.08799 ↗First posted 15 Sep 2023cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

We present SHAPNN, a novel deep tabular data modeling architecture designed for supervised learning. Our approach leverages Shapley values, a well-established technique for explaining black-box models. Our neural network is trained using standard backward propagation optimization methods, and is regularized with realtime estimated Shapley values. Our method offers several advantages, including the ability to provide valid explanations with no computational overhead for data instances and datasets. Additionally, prediction with explanation serves as a regularizer, which improves the model's performance. Moreover, the regularized prediction enhances the model's capability for continual learning. We evaluate our method on various publicly available datasets and compare it with state-of-the-art deep neural network models, demonstrating the superior performance of SHAPNN in terms of AUROC, transparency, as well as robustness to streaming data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 44 references that are in the map. First posted on arXiv 15 Sep 2023.

Builds on

24 of 44 references.

References · 24

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  4. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  5. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  6. 2018Experience Replay for Continual Learningcited by 1,074
  7. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  8. 2019TabNet: Attentive Interpretable Tabular Learningcited by 640
  9. 2017Self-Normalizing Neural Networkscited by 591
  10. 2021Tabular Data: Deep Learning is Not All You Needcited by 530
  11. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  12. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 398
12 more
  1. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  2. 2021SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Trainingcited by 310
  3. 2018CatBoost: gradient boosting with categorical features supportcited by 208
  4. 2019Neural Oblivious Decision Ensembles for Deep Learning on Tabular Datacited by 200
  5. 2022Why do tree-based models still outperform deep learning on tabular data?cited by 198
  6. 2019Class-incremental Learning via Deep Model Consolidationcited by 172
  7. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
  8. 2021Well-tuned Simple Nets Excel on Tabular Datasetscited by 151
  9. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  10. 2017Incremental Learning Through Deep Adaptationcited by 108
  11. 2021Shapley Explanation Networkscited by 41
  12. 2021Attention-like feature explanation for tabular datacited by 3

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024Comparative Analysis of Pooling Mechanisms in LLMs: A Sentiment Analysis Perspectivecited by 12
  2. 2024Enhancing Link Prediction with Fuzzy Graph Attention Networks and Dynamic Negative Samplingcited by 5
  3. 2024FGATT: A Robust Framework for Wireless Data Imputation Using Fuzzy Graph Attention Networks and Transformer Encoderscited by 1
  4. 2025SHAP-Guided Regularization in Machine Learning Modelscited by 0