Flow-Based Attribution in Graphical Models: A Recursive Shapley Approach

Abstract

We study the attribution problem in a graphical model, wherein the objective is to quantify how the effect of changes at the source nodes propagates through the graph. We develop a model-agnostic flow-based attribution method, called recursive Shapley value (RSV). RSV generalizes a number of existing node-based methods and uniquely satisfies a set of flow-based axioms. In addition to admitting a natural characterization for linear models and facilitating mediation analysis for non-linear models, RSV satisfies a mix of desirable properties discussed in the recent literature, including implementation invariance, sensitivity, monotonicity, and affine scale invariance.

Cite

Text

Singal et al. "Flow-Based Attribution in Graphical Models: A Recursive Shapley Approach." International Conference on Machine Learning, 2021.

Markdown

[Singal et al. "Flow-Based Attribution in Graphical Models: A Recursive Shapley Approach." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/singal2021icml-flowbased/)

BibTeX

@inproceedings{singal2021icml-flowbased,
  title     = {{Flow-Based Attribution in Graphical Models: A Recursive Shapley Approach}},
  author    = {Singal, Raghav and Michailidis, George and Ng, Hoiyi},
  booktitle = {International Conference on Machine Learning},
  year      = {2021},
  pages     = {9733-9743},
  volume    = {139},
  url       = {https://mlanthology.org/icml/2021/singal2021icml-flowbased/}
}