Knowledge-based XAI through CBR: There is more to explanations than models can tell
arXiv:2108.10363
Abstract
The underlying hypothesis of knowledge-based explainable artificial intelligence is the data required for data-centric artificial intelligence agents (e.g., neural networks) are less diverse in contents than the data required to explain the decisions of such agents to humans. The idea is that a classifier can attain high accuracy using data that express a phenomenon from one perspective whereas the audience of explanations can entail multiple stakeholders and span diverse perspectives. We hence propose to use domain knowledge to complement the data used by agents. We formulate knowledge-based explainable artificial intelligence as a supervised data classification problem aligned with the CBR methodology. In this formulation, the inputs are case problems composed of both the inputs and outputs of the data-centric agent and case solutions, the outputs, are explanation categories obtained from domain knowledge and subject matter experts. This formulation does not typically lead to an accurate classification, preventing the selection of the correct explanation category. Knowledge-based explainable artificial intelligence extends the data in this formulation by adding features aligned with domain knowledge that can increase accuracy when selecting explanation categories.
arXiv comment12 pages, 8 figures. This paper was accepted at workshop XCBR: Case-Based Reasoning for the Explanation of Intelligent Systems at ICCBR 2021
References in corpus (15)
- A Unified Approach to Interpreting Model Predictions
- Towards A Rigorous Science of Interpretable Machine Learning
- Axiomatic Attribution for Deep Networks
- Learning Important Features Through Propagating Activation Differences
- Understanding Black-box Predictions via Influence Functions
- Explainable Machine Learning for Scientific Insights and Discoveries
- Sanity Checks for Saliency Maps
- A systematic review and taxonomy of explanations in decision support and recommender systems
- Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions
- Explainable Artificial Intelligence: a Systematic Review
- Interpreting Black Box Predictions using Fisher Kernels
- CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humans
- Data Representing Ground-Truth Explanations to Evaluate XAI Methods
- Interpreting Deep Models through the Lens of Data
- Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teaching