Timezone: »

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay
Joao Marques-Silva · Thomas Gerspacher · Martin Cooper · Alexey Ignatiev · Nina Narodytska

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1067

Recent work proposed the computation of so-called PI-explanations of Naive Bayes Classifiers (NBCs). PI-explanations are subset-minimal sets of feature-value pairs that are sufficient for the prediction, and have been computed with state-of-the-art exact algorithms that are worst-case exponential in time and space. In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers. Furthermore, we show that the enumeration of PI-explanations can be obtained with polynomial delay. Experimental results demonstrate the performance gains of the new algorithms when compared with earlier work. The experimental results also investigate ways to measure the quality of heuristic explanations.

Author Information

Joao Marques-Silva (ANITI, Federal University of Toulouse Midi-Pyrénées)
Thomas Gerspacher (ANITI)
Martin Cooper (University of Toulouse 3)
Alexey Ignatiev (Monash University)
Nina Narodytska (VMmare Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors

  • 2019 Poster: On Relating Explanations and Adversarial Examples »
    Alexey Ignatiev · Nina Narodytska · Joao Marques-Silva
  • 2017 : Poster Spotlights I »
    Taesik Na · Yang Song · Aman Sinha · Richard Shin · Qiuyuan Huang · Nina Narodytska · Matthew Staib · Kexin Pei · Fnu Suya · Amirata Ghorbani · Jacob Buckman · Matthias Hein · Huan Zhang · Yanjun Qi · Yuan Tian · Min Du · Dimitris Tsipras