Files and links (1)
CC BY V4.0, Open Access
Preprint
ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
ArXiv.org
Cornell University
2025
Abstract
Explainable Artificial Intelligence (XAI) methods, such as Local Interpretable Model-Agnostic Explanations (LIME), have advanced the interpretability of black-box machine learning models by approximating their behavior locally using interpretable surrogate models. However, LIME's inherent randomness in perturbation and sampling can lead to locality and instability issues, especially in scenarios with limited training data. In such cases, data scarcity can result in the generation of unrealistic variations and samples that deviate from the true data manifold. Consequently, the surrogate model may fail to accurately approximate the complex decision boundary of the original model. To address these challenges, we propose a novel Instance-based Transfer Learning LIME framework (ITL-LIME) that enhances explanation fidelity and stability in data-constrained environments. ITL-LIME introduces instance transfer learning into the LIME framework by leveraging relevant real instances from a related source domain to aid the explanation process in the target domain. Specifically, we employ clustering to partition the source domain into clusters with representative prototypes. Instead of generating random perturbations, our method retrieves pertinent real source instances from the source cluster whose prototype is most similar to the target instance. These are then combined with the target instance's neighboring real instances. To define a compact locality, we further construct a contrastive learning-based encoder as a weighting mechanism to assign weights to the instances from the combined set based on their proximity to the target instance. Finally, these weighted source and target instances are used to train the surrogate model for explanation purposes.
Details
- Title
- ITL-LIME: Instance-Based Transfer Learning for Enhancing Local Explanations in Low-Resource Data Settings
- Authors/Creators
- Rehan RazaGuanjin WangKevin WongHamid LagaMarco Fisichella
- Publication Details
- ArXiv.org
- Publisher
- Cornell University
- Identifiers
- 991005807242407891
- Copyright
- © the Authors
- Murdoch Affiliation
- Centre for Biosecurity and One Health; School of Information Technology; Centre for Healthy Ageing; Centre for Water, Energy and Waste
- Language
- English
- Resource Type
- Preprint
Metrics
1 File views/ downloads
15 Record Views