Sparse and Faithful Explanations Without Sparse Models
CoRR(2024)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要