# Who's responsible? Jointly quantifying the contribution of the learning algorithm and training data

arXiv: https://arxiv.org/abs/1910.04214 · HTML: https://mlsanity.com/paper/1910.04214/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Data Banzhaf: A Robust Data Valuation Framework for Machine Learning](https://mlsanity.com/paper/2205.15466/) (2022)
- [Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search](https://mlsanity.com/paper/2206.09811/) (2022)
- [Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation](https://mlsanity.com/paper/2308.15709/) (2023)
- [2D-Shapley: A Framework for Fragmented Data Valuation](https://mlsanity.com/paper/2306.10473/) (2023)
- [Shapley Based Residual Decomposition for Instance Analysis](https://mlsanity.com/paper/2305.18818/) (2023)
- [LossVal: Efficient Data Valuation for Neural Networks](https://mlsanity.com/paper/2412.04158/) (2024)
- [A case for data valuation transparency via DValCards](https://mlsanity.com/paper/2506.23349/) (2025)

## Abstract (arXiv)

A learning algorithm A trained on a dataset D is revealed to have poor performance on some subpopulation at test time. Where should the responsibility for this lay? It can be argued that the data is responsible, if for example training A on a more representative dataset D' would have improved the performance. But it can similarly be argued that A itself is at fault, if training a different variant A' on the same dataset D would have improved performance. As ML becomes widespread and such failure cases more common, these types of questions are proving to be far from hypothetical. With this motivation in mind, in this work we provide a rigorous formulation of the joint credit assignment problem between a learning algorithm A and a dataset D. We propose Extended Shapley as a principled framework for this problem, and experiment empirically with how it can be used to address questions of ML accountability.