Relation-Based Counterfactual Explanations for Bayesian Network Classifiers
Authors: Emanuele Albini, Antonio Rago, Pietro Baroni, Francesca Toni
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We then prove empirically for various BCs that CFXs provide useful information in real world settings, e.g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature. We now evaluate CFXs empirically with various datasets and BCs. Our experiments indicate that CFXs (i) are of appropriate cardinality and length (compared with PIXs and MCXs from Section 4); (ii) highlight paths via PIs towards CIs; and (iii) give meaningful information about BCs predictions. Table 3 shows our results concerning the explanations cardinality and length. |
| Researcher Affiliation | Academia | 1Dipartimento di Ingegneria dell Informazione, Universit a degli Studi di Brescia, Italy 2Department of Computing, Imperial College London, UK |
| Pseudocode | No | The paper describes the algorithms for generating R! and R in paragraph text in Section 5, but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any specific repository links or explicit statements about code release for the methodology described. |
| Open Datasets | Yes | The Congressional Voting Records dataset3, the Parole Violation dataset4 and the Child Bayesian network5. 3http://archive.ics.uci.edu/ml/index.php 4https://www.icpsr.umich.edu/icpsrweb/NACJD/studies/26521 5https://www.bnlearn.com/bnrepository/discrete-medium.html |
| Dataset Splits | No | The paper mentions 'test set accuracy' but does not specify train/validation/test splits or mention a validation set. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with versions). |
| Experiment Setup | No | The paper states, 'In each BC, classifications values in evaluations are set to those with the highest probability,' but does not provide specific hyperparameters, detailed training configurations, or other system-level settings for experimental reproduction. |