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 denied to
someone because they have no credit history, which overwhelms any evidence
towards their creditworthiness. In this work, we introduce the Sparse
Explanation Value (SEV), a new way of measuring sparsity in machine learning
models. In the loan denial example above, the SEV is 1 because only one factor
is needed to explain why the loan was denied. SEV is a measure of decision
sparsity rather than overall model sparsity, and we are able to show that many
machine learning models -- even if they are not sparse -- actually have low
decision sparsity, as measured by SEV. SEV is defined using movements over a
hypercube, allowing SEV to be defined consistently over various model classes,
with movement restrictions reflecting real-world constraints. We proposed the
algorithms that reduce SEV without sacrificing accuracy, providing sparse and
completely faithful explanations, even without globally sparse models.

在这项工作中，我们引入了稀疏解释值（SEV），一种衡量机器学习模型稀疏性的新方法。我们能够证明，许多机器学习模型实际上具有低的决策稀疏度（由 SEV 度量），即使它们不是稀疏的。SEV 利用超立方体中的运动来定义，使得 SEV 能够在各种模型类中一致地定义，并且运动限制反映了现实世界的约束。我们提出了一种算法，可以在不牺牲准确性的情况下减少 SEV，提供稀疏且完全忠实的解释，即使没有全局稀疏模型。