MeLIME: Meaningful Local Explanation for Machine Learning Models
arXiv:2009.05818
Abstract
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 address this problem. In this work, we introduce strategies to improve local explanations taking into account the distribution of the data used to train the black-box models. We show that our approach, MeLIME, produces more meaningful explanations compared to other techniques over different ML models, operating on various types of data. MeLIME generalizes the LIME method, allowing more flexible perturbation sampling and the use of different local interpretable models. Additionally, we introduce modifications to standard training algorithms of local interpretable models fostering more robust explanations, even allowing the production of counterfactual examples. To show the strengths of the proposed approach, we include experiments on tabular data, images, and text; all showing improved explanations. In particular, MeLIME generated more meaningful explanations on the MNIST dataset than methods such as GuidedBackprop, SmoothGrad, and Layer-wise Relevance Propagation. MeLIME is available on https://github.com/tiagobotari/melime.
References in corpus (19)
- Scikit-learn: Machine Learning in Python
- Distributed Representations of Words and Phrases and their Compositionality
- A Survey on Deep Learning in Medical Image Analysis
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- End to End Learning for Self-Driving Cars
- Language Models are Few-Shot Learners
- An Introduction to Variational Autoencoders
- Striving for Simplicity: The All Convolutional Net
- A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
- European Union regulations on algorithmic decision-making and a "right to explanation"
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
- SmoothGrad: removing noise by adding noise
- An unexpected unity among methods for interpreting model predictions
- On the Robustness of Interpretability Methods
- Locally Interpretable Models and Effects based on Supervised Partitioning (LIME-SUP)
- NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks
- iNNvestigate neural networks!
- NLS: an accurate and yet easy-to-interpret regression method