Abstract
Shapley values of individual instances were recently proposed for the problem of data valuation. They were defined as the average marginal instance contributions to the performance of a given predictor. In this paper we propose to use Shapley values of individual instances as conformity scores. To compute these values efficiently and exactly we employ a standard algorithm based on nearest neighbor classification and propose a variant of this algorithm for clustered data. Both variants are used for computing Shapley conformity scores for inductive conformal predictors. The experiments show that the Shapley-value conformity scores result in smaller prediction sets for significance level compared with those produced by standard conformity scores (i.e. similarity between true and predicted output values).
Original language | English |
---|---|
Title of host publication | Proceedings of Machine Learning Research |
Subtitle of host publication | Volume 152: Conformal and Probabilistic Prediction and Applications |
Pages | 52-71 |
Volume | 152 |
Publication status | Published - 2021 |
Event | 10th Conformal and Probabilistic Prediction and Applications 2021 - Online, Centre for Reliable Machine Learning, Egham, United Kingdom Duration: 8 Sept 2021 → 10 Sept 2021 https://cml.rhul.ac.uk/copa2021/ |
Conference
Conference | 10th Conformal and Probabilistic Prediction and Applications 2021 |
---|---|
Abbreviated title | COPA 2021 |
Country/Territory | United Kingdom |
City | Egham |
Period | 8/09/21 → 10/09/21 |
Internet address |