Improving Decision Sparsity
Sparsity is a central aspect of interpretability in machine learning. Typically, sparsity is measured in terms of the size of a model globally, such as the number of variables it uses. However, this notion of sparsity is not particularly relevant for decision-making; someone subjected to a decision does not care about variables that do not contribute to the decision. In this work, we dramatically expand a notion of decision sparsity called the Sparse Explanation Value(SEV) so that its explanations are more meaningful. SEV considers movement along a hypercube towards a reference point. By allowing flexibility in that reference and by considering how distances along the hypercube translate to distances in feature space, we can derive sparser and more meaningful explanations for various types of function classes. We present cluster-based SEV and its variant tree-based SEV, introduce a method that improves credibility of explanations, and propose algorithms that optimize decision sparsity in machine learning models.
Code (1)
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
Sparsity in Optimal Randomized Classification Trees
Decision trees are popular Classification and Regression tools and, when small-sized, easy to interpret. Traditionally, a greedy approach has been used to build the trees, yielding a very fast training process; however, …
ClassificationGeneral ClassificationSparse and Faithful Explanations Without Sparse Models
Even if a model is not globally sparse, it is possible for decisions made from that model to be accurately and faithfully described by a small number of features. For instance, an application for a large loan might be de…
Inference for relative sparsity
In healthcare, there is much interest in estimating policies, or mappings from covariates to treatment decisions. Recently, there is also interest in constraining these estimated policies to the standard of care, which g…
Improved prediction rule ensembling through model-based data generation
Prediction rule ensembles (PRE) provide interpretable prediction models with relatively high accuracy.PRE obtain a large set of decision rules from a (boosted) decision tree ensemble, and achieves sparsitythrough applica…
PredictionregressionThe Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision
Resource efficiency plays an important role for machine learning nowadays. The energy and decision latency are two critical aspects to ensure a sustainable and practical application. Unfortunately, the energy consumption…
image-classificationImage Classification