Efficient SAGE Estimation via Causal Structure Learning
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.
Code (1)
Similar Papers 제목 키워드 기반
Estimating complex causal effects from incomplete observational data
Despite the major advances taken in causal modeling, causality is still an unfamiliar topic for many statisticians. In this paper, it is demonstrated from the beginning to the end how causal effects can be estimated from…
Additive modelsImputationEstimating Heterogeneous Causal Effect of Polysubstance Usage on Drug Overdose from Large-Scale Electronic Health Record
Drug overdose has become a public health crisis in the United States with devastating consequences. However, most of the drug overdose incidences are the consequence of recitative polysubstance usage over a defined perio…
Causal InferenceCooperative Causal GraphSAGE
GraphSAGE is a widely used graph neural network. The introduction of causal inference has improved its robust performance and named as Causal GraphSAGE. However, Causal GraphSAGE focuses on measuring causal weighting amo…
Causal InferenceGraph Neural NetworkCausal Message Passing for Experiments with Unknown and General Network Interference
Randomized experiments are a powerful methodology for data-driven evaluation of decisions or interventions. Yet, their validity may be undermined by network interference. This occurs when the treatment of one unit impact…
Experimental DesignHeterophilic Graph Neural Networks Optimization with Causal Message-passing
In this work, we discover that causal inference provides a promising approach to capture heterophilic message-passing in Graph Neural Network (GNN). By leveraging cause-effect analysis, we can discern heterophilic edges …
Causal InferenceGraph LearningGraph Neural NetworkLink Prediction+1