Blog
About

1
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Explaining Predictions from Tree-based Boosting Ensembles

      Preprint

      , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Understanding how "black-box" models arrive at their predictions has sparked significant interest from both within and outside the AI community. Our work focuses on doing this by generating local explanations about individual predictions for tree-based ensembles, specifically Gradient Boosting Decision Trees (GBDTs). Given a correctly predicted instance in the training set, we wish to generate a counterfactual explanation for this instance, that is, the minimal perturbation of this instance such that the prediction flips to the opposite class. Most existing methods for counterfactual explanations are (1) model-agnostic, so they do not take into account the structure of the original model, and/or (2) involve building a surrogate model on top of the original model, which is not guaranteed to represent the original model accurately. There exists a method specifically for random forests; we wish to extend this method for GBDTs. This involves accounting for (1) the sequential dependency between trees and (2) training on the negative gradients instead of the original labels.

          Related collections

          Most cited references 4

          • Record: found
          • Abstract: not found
          • Article: not found

          Multi-class AdaBoost

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Explanation in artificial intelligence: Insights from the social sciences

             Tim Miller (2019)
              Bookmark
              • Record: found
              • Abstract: not found
              • Book Chapter: not found

              Explaining Recommendations

               Nava Tintarev (2020)
                Bookmark

                Author and article information

                Journal
                04 July 2019
                Article
                1907.02582

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                Custom metadata
                SIGIR 2019: FACTS-IR Workshop
                cs.LG cs.AI cs.IR stat.ML

                Information & Library science, Machine learning, Artificial intelligence

                Comments

                Comment on this article