Knowledge-based XAI through CBR: There is more to explanations than models can tell
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 23 Aug 2021.
Builds on
28 of 49 references.
References · 28
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
- 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 476
- 2017The (Un)reliability of saliency methodscited by 333
- 2017Real Time Image Saliency for Black Box Classifierscited by 246
16 more
- 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
- 2018Representer Point Selection for Explaining Deep Neural Networkscited by 187
- 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 166
- 2019Interpretations are useful: penalizing explanations to align neural networks with prior knowledgecited by 145
- 2020Making deep neural networks right for the right scientific reasons by interacting with their explanationscited by 142
- 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
- 2015The Bayesian Case Model: A Generative Approach for Case-Based Reasoning and Prototype Classificationcited by 76
- 2018Interpreting Black Box Predictions using Fisher Kernelscited by 48
- 2020A systematic review and taxonomy of explanations in decision support and recommender systemscited by 45
- 2018Content-Based Citation Recommendationcited by 43
- 2018Learning Finite State Representations of Recurrent Policy Networkscited by 37
- 2018CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humanscited by 14
- 2020Explanation Ontology: A Model of Explanations for User-Centered AIcited by 13
- 2020Data Representing Ground-Truth Explanations to Evaluate XAI Methodscited by 7
- 2020Interpreting Deep Models through the Lens of Datacited by 3
- 2021Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teachingcited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.