Scalable SHAP-Informed Neural Network
In the pursuit of scalable optimization strategies for neural networks, this study addresses the computational challenges posed by SHAP-informed learning methods introduced in prior work. Specifically, we extend the SHAP-based optimization family by incorporating two existing approximation methods,...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/13/2152 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849704284121202688 |
|---|---|
| author | Jarrod Graham Victor S. Sheng |
| author_facet | Jarrod Graham Victor S. Sheng |
| author_sort | Jarrod Graham |
| collection | DOAJ |
| description | In the pursuit of scalable optimization strategies for neural networks, this study addresses the computational challenges posed by SHAP-informed learning methods introduced in prior work. Specifically, we extend the SHAP-based optimization family by incorporating two existing approximation methods, C-SHAP and FastSHAP, to reduce training time while preserving the accuracy and generalization benefits of SHAP-based adjustments. C-SHAP leverages clustered SHAP values for efficient learning rate modulation, while FastSHAP provides rapid approximations of feature importance for gradient adjustment. Together, these methods significantly improve the practical usability of SHAP-informed neural network training by lowering computational overhead without major sacrifices in predictive performance. The experiments conducted across four datasets—Breast Cancer, Ames Housing, Adult Census, and California Housing—demonstrate that both C-SHAP and FastSHAP achieve substantial reductions in training time compared to original SHAP-based methods while maintaining competitive test losses, RMSE, and accuracy relative to baseline Adam optimization. Additionally, a hybrid approach combining C-SHAP and FastSHAP is explored as an avenue for further balancing performance and efficiency. These results highlight the feasibility of using feature-importance-based guidance to enhance optimization in neural networks at a reduced computational cost, paving the way for broader applicability of explainability-informed training strategies. |
| format | Article |
| id | doaj-art-83225442b9454ce2899dfcb3f0a1b415 |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-83225442b9454ce2899dfcb3f0a1b4152025-08-20T03:16:47ZengMDPI AGMathematics2227-73902025-06-011313215210.3390/math13132152Scalable SHAP-Informed Neural NetworkJarrod Graham0Victor S. Sheng1Department of Computer Science, College of Engineering, Texas Tech University, Lubbock, TX 79409, USADepartment of Computer Science, College of Engineering, Texas Tech University, Lubbock, TX 79409, USAIn the pursuit of scalable optimization strategies for neural networks, this study addresses the computational challenges posed by SHAP-informed learning methods introduced in prior work. Specifically, we extend the SHAP-based optimization family by incorporating two existing approximation methods, C-SHAP and FastSHAP, to reduce training time while preserving the accuracy and generalization benefits of SHAP-based adjustments. C-SHAP leverages clustered SHAP values for efficient learning rate modulation, while FastSHAP provides rapid approximations of feature importance for gradient adjustment. Together, these methods significantly improve the practical usability of SHAP-informed neural network training by lowering computational overhead without major sacrifices in predictive performance. The experiments conducted across four datasets—Breast Cancer, Ames Housing, Adult Census, and California Housing—demonstrate that both C-SHAP and FastSHAP achieve substantial reductions in training time compared to original SHAP-based methods while maintaining competitive test losses, RMSE, and accuracy relative to baseline Adam optimization. Additionally, a hybrid approach combining C-SHAP and FastSHAP is explored as an avenue for further balancing performance and efficiency. These results highlight the feasibility of using feature-importance-based guidance to enhance optimization in neural networks at a reduced computational cost, paving the way for broader applicability of explainability-informed training strategies.https://www.mdpi.com/2227-7390/13/13/2152SHAPAdam optimizerlearning rate adjustmentsneural networksgrid searchperformance evaluation |
| spellingShingle | Jarrod Graham Victor S. Sheng Scalable SHAP-Informed Neural Network Mathematics SHAP Adam optimizer learning rate adjustments neural networks grid search performance evaluation |
| title | Scalable SHAP-Informed Neural Network |
| title_full | Scalable SHAP-Informed Neural Network |
| title_fullStr | Scalable SHAP-Informed Neural Network |
| title_full_unstemmed | Scalable SHAP-Informed Neural Network |
| title_short | Scalable SHAP-Informed Neural Network |
| title_sort | scalable shap informed neural network |
| topic | SHAP Adam optimizer learning rate adjustments neural networks grid search performance evaluation |
| url | https://www.mdpi.com/2227-7390/13/13/2152 |
| work_keys_str_mv | AT jarrodgraham scalableshapinformedneuralnetwork AT victorssheng scalableshapinformedneuralnetwork |