Gaining insight through case-based explanation
By Conor Nugent, Dónal Doyle, Padraig Cunningham. 2009
59 citations recorded by the source corpus.
Traditional explanation strategies in machine learning have been dominated by rule and decision tree based approaches. Case-based explanations represent an alternative approach which has inherent advantages in terms of transparency and user acceptability. Case-based explanations are based on a strategy of presenting similar past examples in support of and as justification for recommendations made. The traditional approach to such explanations, of simply supplying the nearest neighbour as an explanation, has been found to have shortcomings. Cases should be selected based on their utility in forming useful explanations. However, the relevance of the explanation case may not be clear to the end user as it is retrieved using domain knowledge which they themselves may not have. In this paper the focus is on a knowledge-light approach to case-based explanations that works by selecting cases based on explanation utility and offering insights into the effects of feature-value differences. In this paper we examine to two such a knowledge-light frameworks for case-based explanation. We look at explanation oriented retrieval (EOR) a strategy which explicitly models explanation utility and also at the knowledge-light explanation framework (KLEF) that uses local logistic regression to support case-based explanation.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Eoin M. Kenny
- Nicholas Mattei
- Thomas Dodson
- Judy Goldsmith
- Or Biran
- Courtenay V. Cotton
- Mark T. Keane
Citations in the corpus
- The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning (2019, background): “Significantly, this group also performed a number of controlled user tests to see whether the retrieved cases had any explanatory value, finding that provision of cases improved user satisfaction of the system [Nugent et al., 2009].”
- Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…Cassens, and Aamodt, 2008; Lacave and Díez, 2002; Letham, Rudin, McCormick, Madigan, and others, 2015; Liang and Van den Broeck, 2017; Nugent, Doyle, and Cunningham, 2009; Papadimitiou, Symeonidis and Manolopoulos, 2012; Pearl, 1988; Suermondt, 1992; Shafto and Goodman, 2008; Shafto,…”
- How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, background): “The Irish researchers, who did not cite the Korean work, proposed a new and intriguing local feature-weighting method [74-76].”
- Explanation and Justification in Machine Learning : A Survey Or (2017, methodology): “One example is [Nugent et al. , 2009] who proposed a case-based method of explanation for decision support systems, where alternative samples are selected and the explanation focuses on how they differ (if the decision is different) or their similarities (otherwise).”
- A Natural Language Argumentation Interface for Explanation Generation in Markov Decision Processes (2011, methodology): “’s KLEF [14] is an example of a case-based explanation system.”