Efficient SAGE Estimation via Causal Structure Learning

要約

タイトル：因果構造学習による効率的なSAGE推定

要約：

– SAGE（Shapley Additive Global Importance）値は、正確な計算には指数的な特徴集合の余剰パフォーマンス寄与度を必要とするため計算コストが非常に高い。
– そのため、SAGEの近似アルゴリズムは、特徴集合の一部のみを考慮に入れている。
– この問題に対する提案手法$d$-SAGEは、因果構造学習によって条件独立性を特定し、余剰寄与度の計算をスキップすることで、SAGEの近似を加速する。
– empiricallyによって、$d$-SAGEはSAGE値の効率的かつ正確な推定を可能にすることが示された。

要約(オリジナル)

The Shapley Additive Global Importance (SAGE) value is a theoretically appealing interpretability method that fairly attributes global importance to a model’s features. However, its exact calculation requires the computation of the feature’s surplus performance contributions over an exponential number of feature sets. This is computationally expensive, particularly because estimating the surplus contributions requires sampling from conditional distributions. Thus, SAGE approximation algorithms only take a fraction of the feature sets into account. We propose $d$-SAGE, a method that accelerates SAGE approximation. $d$-SAGE is motivated by the observation that conditional independencies (CIs) between a feature and the model target imply zero surplus contributions, such that their computation can be skipped. To identify CIs, we leverage causal structure learning (CSL) to infer a graph that encodes (conditional) independencies in the data as $d$-separations. This is computationally more efficient because the expense of the one-time graph inference and the $d$-separation queries is negligible compared to the expense of surplus contribution evaluations. Empirically we demonstrate that $d$-SAGE enables the efficient and accurate estimation of SAGE values.

arxiv情報

提供元, 利用サービス

arxiv.jp, OpenAI