Causal Interpretability for Machine Learning – Problems, Methods and Evaluation

@article{causalinterpretability-kddnews22,
   address = {New York, NY, USA},
   apice = {CausalinterpretabilityKddnews22},
   author = {Raha Moraffah and Mansooreh Karami and Ruocheng Guo and Adrienne Raglin and Huan Liu},
   doi = {10.1145/3400051.3400058},
   issn = {1931-0145},
   journal = {ACM SIGKDD Explorations Newsletter},
   keywords = {counterfactuals, interpratablity, causal inference, explainability, machine learning},
   month = jun,
   number = 1,
   numpages = 16,
   pages = {18--33},
   publisher = {Association for Computing Machinery (ACM)},
   title = {Causal Interpretability for Machine Learning – Problems, Methods and Evaluation},
   url = {https://doi.org/10.1145/3400051.3400058},
   urlopenaccess = {http://www.kdd.org/exploration_files/4._CR._25._Causal_Explainability_Survey-final.pdf},
   volume = 22,
   year = 2020
}