# Unified Shapley Framework to Explain Prediction Drift

arXiv: https://arxiv.org/abs/2102.07862 · HTML: https://mlsanity.com/paper/2102.07862/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 53 references that are in the map.
- First posted on arXiv 15 Feb 2021.

## Builds on (most cited first, 12 of 12)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Wasserstein Fair Classification](https://mlsanity.com/paper/1907.12059/) (2019)
- [A Distributional Framework for Data Valuation](https://mlsanity.com/paper/2002.12334/) (2020)
- [FlipTest: Fairness Testing via Optimal Transport](https://mlsanity.com/paper/1906.09218/) (2019)
- [Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model](https://mlsanity.com/paper/1804.01947/) (2018)
- [Explainability for fair machine learning](https://mlsanity.com/paper/2010.07389/) (2020)
- [Concept Drift Detection for Streaming Data](https://mlsanity.com/paper/1504.01044/) (2015)
- [Wasserstein-based fairness interpretability framework for machine learning models](https://mlsanity.com/paper/2011.03156/) (2020)
- [Automatic Model Monitoring for Data Streams](https://mlsanity.com/paper/1908.04240/) (2019)
- [ML Health: Fitness Tracking for Production Models](https://mlsanity.com/paper/1902.02808/) (2019)

## Built on by (most cited first, 5 of 5)

- [Towards Explaining Distribution Shifts](https://mlsanity.com/paper/2210.10275/) (2022)
- [FairCanary: Rapid Continuous Explainable Fairness](https://mlsanity.com/paper/2106.07057/) (2021)
- [ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values](https://mlsanity.com/paper/2604.11200/) (2026)
- [FMMO: Detecting the Divergence Between Local Attribution and Global Drift](https://mlsanity.com/paper/2609.06173/) (2026)
- [Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs](https://mlsanity.com/paper/2610.16534/) (2026)

## Abstract (arXiv)

Predictions are the currency of a machine learning model, and to understand the model's behavior over segments of a dataset, or over time, is an important problem in machine learning research and practice. There currently is no systematic framework to understand this drift in prediction distributions over time or between two semantically meaningful slices of data, in terms of the input features and points. We propose GroupShapley and GroupIG (Integrated Gradients), as axiomatically justified methods to tackle this problem. In doing so, we re-frame all current feature/data importance measures based on the Shapley value as essentially problems of distributional comparisons, and unify them under a common umbrella. We axiomatize certain desirable properties of distributional difference, and study the implications of choosing them empirically.