A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost
Abstract The success of machine learning in real-world use cases has increased its demand in mission-critical applications such as autonomous vehicles, healthcare and medical diagnosis, aviation and flight safety, natural disaster prediction, early warning systems, etc. Adaptive Boosting (AdaBoost)...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2024-09-01
|
| Series: | Human-Centric Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44230-024-00082-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544571143585792 |
|---|---|
| author | Raj Joseph Kiran J. Sanil S. Asharaf |
| author_facet | Raj Joseph Kiran J. Sanil S. Asharaf |
| author_sort | Raj Joseph Kiran |
| collection | DOAJ |
| description | Abstract The success of machine learning in real-world use cases has increased its demand in mission-critical applications such as autonomous vehicles, healthcare and medical diagnosis, aviation and flight safety, natural disaster prediction, early warning systems, etc. Adaptive Boosting (AdaBoost) is an ensemble learning method that has gained much traction in such applications. Inherently being a non-interpretable model, the interpretability of the AdaBoost algorithm has been a research topic for many years. Furthermore, most of the research being conducted till now is aimed at explaining AdaBoost using perturbation-based techniques. The paper presents a technique to interpret the AdaBoost algorithm from a data perspective using deletion diagnostics and Cook’s distance. The technique achieves interpretability by detecting the most influential data instances and their impact on the feature importance of the model. This interpretability enables domain experts to accurately modify the significance of specific features in a trained AdaBoost model depending on the data instances. Unlike explaining AdaBoost using perturbation-based techniques, interpreting from a data perspective will enable it to debug data-related biases, errors and to impart the knowledge of the domain experts into the model through domain aware fine-tuning. Experimental studies were conducted with diverse real-world multi-feature datasets to demonstrate interpretability and knowledge integration through domain-aware fine-tuning. |
| format | Article |
| id | doaj-art-260707f480924621a2f662de61171f09 |
| institution | Kabale University |
| issn | 2667-1336 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | Springer Nature |
| record_format | Article |
| series | Human-Centric Intelligent Systems |
| spelling | doaj-art-260707f480924621a2f662de61171f092025-01-12T12:26:39ZengSpringer NatureHuman-Centric Intelligent Systems2667-13362024-09-014461063210.1007/s44230-024-00082-2A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoostRaj Joseph Kiran0J. Sanil1S. Asharaf2School of Computer Science and Engineering, Kerala University of Digital Sciences, Innovation and TechnologySchool of Computer Science and Engineering, Kerala University of Digital Sciences, Innovation and TechnologySchool of Computer Science and Engineering, Kerala University of Digital Sciences, Innovation and TechnologyAbstract The success of machine learning in real-world use cases has increased its demand in mission-critical applications such as autonomous vehicles, healthcare and medical diagnosis, aviation and flight safety, natural disaster prediction, early warning systems, etc. Adaptive Boosting (AdaBoost) is an ensemble learning method that has gained much traction in such applications. Inherently being a non-interpretable model, the interpretability of the AdaBoost algorithm has been a research topic for many years. Furthermore, most of the research being conducted till now is aimed at explaining AdaBoost using perturbation-based techniques. The paper presents a technique to interpret the AdaBoost algorithm from a data perspective using deletion diagnostics and Cook’s distance. The technique achieves interpretability by detecting the most influential data instances and their impact on the feature importance of the model. This interpretability enables domain experts to accurately modify the significance of specific features in a trained AdaBoost model depending on the data instances. Unlike explaining AdaBoost using perturbation-based techniques, interpreting from a data perspective will enable it to debug data-related biases, errors and to impart the knowledge of the domain experts into the model through domain aware fine-tuning. Experimental studies were conducted with diverse real-world multi-feature datasets to demonstrate interpretability and knowledge integration through domain-aware fine-tuning.https://doi.org/10.1007/s44230-024-00082-2AdaBoostDeletion diagnosticsInfluential instancesInterpretable machine learning |
| spellingShingle | Raj Joseph Kiran J. Sanil S. Asharaf A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost Human-Centric Intelligent Systems AdaBoost Deletion diagnostics Influential instances Interpretable machine learning |
| title | A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost |
| title_full | A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost |
| title_fullStr | A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost |
| title_full_unstemmed | A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost |
| title_short | A Novel Approach for Model Interpretability and Domain Aware Fine-Tuning in AdaBoost |
| title_sort | novel approach for model interpretability and domain aware fine tuning in adaboost |
| topic | AdaBoost Deletion diagnostics Influential instances Interpretable machine learning |
| url | https://doi.org/10.1007/s44230-024-00082-2 |
| work_keys_str_mv | AT rajjosephkiran anovelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost AT jsanil anovelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost AT sasharaf anovelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost AT rajjosephkiran novelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost AT jsanil novelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost AT sasharaf novelapproachformodelinterpretabilityanddomainawarefinetuninginadaboost |