Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach

2022-11-02 · Arnab Neelim Mazumder, Niall Lyons, Ashutosh Pandey, Avik Santra, Tinoosh Mohsenin

Explainability of neural network prediction is essential to understand feature importance and gain interpretable insight into neural network performance. However, explanations of neural network outcomes are mostly limited to visualization, and there is scarce work that looks to use these explanations as feedback to improve model performance. In this work, model explanations are fed back to the feed-forward training to help the model generalize better. To this extent, a custom weighted loss where the weights are generated by considering the Euclidean distances between true LIME (Local Interpretable Model-Agnostic Explanations) explanations and model-predicted LIME explanations is proposed. Also, in practical training scenarios, developing a solution that can help the model learn sequentially without losing information on previous data distribution is imperative due to the unavailability of all the training data at once. Thus, the framework incorporates the custom weighted loss with Elastic Weight Consolidation (EWC) to maintain performance in sequential testing sets. The proposed custom training procedure results in a consistent enhancement of accuracy ranging from 0.5% to 1.5% throughout all phases of the incremental learning setup compared to traditional loss-based training methods for the keyword spotting task using the Google Speech Commands dataset.

📄 PDF Abstract BibTeX arXiv:2211.01413

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Importance Incremental Learning Keyword Spotting

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

EWC The methon to overcome catastrophic forgetting in neural network while continual learning

SLICE: Stabilized LIME for Consistent Explanations for Image Classification

2024-01-01 · CVPR 2024 1 · Revoti Prasad Bora, Philipp Terhörst, Raymond Veldhuis, Raghavendra Ramachandra 외

Local Interpretable Model-agnostic Explanations (LIME) - a widely used post-ad-hoc model agnostic explainable AI (XAI) technique. It works by training a simple transparent (surrogate) model using random samples drawn…

feature selection image-classification Image Classification Superpixels

bLIMEy: Surrogate Prediction Explanations Beyond LIME

2019-10-29 · Kacper Sokol, Alexander Hepburn, Raul Santos-Rodriguez, Peter Flach

Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are…

Explainable artificial intelligence Prediction

Q-LIME $π$: A Quantum-Inspired Extension to LIME

2024-12-23 · Nelson Colón Vargas

Machine learning models offer powerful predictive capabilities but often lack transparency. Local Interpretable Model-agnostic Explanations (LIME) addresses this by perturbing features and measuring their impact on a mod…

DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems

2019-06-24 · Muhammad Rehman Zafar, Naimul Mefraz Khan

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanatio…

Clustering Feature Importance feature selection

MeLIME: Meaningful Local Explanation for Machine Learning Models

2020-09-12 · Tiago Botari, Frederik Hvilshøj, Rafael Izbicki, Andre C. P. L. F. de Carvalho

Most state-of-the-art machine learning algorithms induce black-box models, preventing their application in many sensitive domains. Hence, many methodologies for explaining machine learning models have been proposed to ad…

BIG-bench Machine Learning counterfactual