Saved in:
Bibliographic Details
Main Authors: Fermanian, Jean-Baptiste, Humbert, Pierre, Blanchard, Gilles
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.11384
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912744605745152
author Fermanian, Jean-Baptiste
Humbert, Pierre
Blanchard, Gilles
author_facet Fermanian, Jean-Baptiste
Humbert, Pierre
Blanchard, Gilles
contents We introduce a method based on Conformal Prediction (CP) to quantify the uncertainty of full ranking algorithms. We focus on a specific scenario where $n+m$ items are to be ranked by some ``black box'' algorithm. It is assumed that the relative (ground truth) ranking of $n$ of them is known. The objective is then to quantify the error made by the algorithm on the ranks of the $m$ new items among the total $(n+m)$. In such a setting, the true ranks of the $n$ original items in the total $(n+m)$ depend on the (unknown) true ranks of the $m$ new ones. Consequently, we have no direct access to a calibration set to apply a classical CP method. To address this challenge, we propose to construct distribution-free bounds of the unknown conformity scores using recent results on the distribution of conformal p-values. Using these scores upper bounds, we provide valid prediction sets for the rank of any item. We also control the false coverage proportion, a crucial quantity when dealing with multiple prediction sets. Finally, we empirically show on both synthetic and real data the efficiency of our CP method for state-of-the-art algorithms such as RankNet or LambdaMart.
format Preprint
id arxiv_https___arxiv_org_abs_2501_11384
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transductive Conformal Inference for Full Ranking
Fermanian, Jean-Baptiste
Humbert, Pierre
Blanchard, Gilles
Machine Learning
Methodology
We introduce a method based on Conformal Prediction (CP) to quantify the uncertainty of full ranking algorithms. We focus on a specific scenario where $n+m$ items are to be ranked by some ``black box'' algorithm. It is assumed that the relative (ground truth) ranking of $n$ of them is known. The objective is then to quantify the error made by the algorithm on the ranks of the $m$ new items among the total $(n+m)$. In such a setting, the true ranks of the $n$ original items in the total $(n+m)$ depend on the (unknown) true ranks of the $m$ new ones. Consequently, we have no direct access to a calibration set to apply a classical CP method. To address this challenge, we propose to construct distribution-free bounds of the unknown conformity scores using recent results on the distribution of conformal p-values. Using these scores upper bounds, we provide valid prediction sets for the rank of any item. We also control the false coverage proportion, a crucial quantity when dealing with multiple prediction sets. Finally, we empirically show on both synthetic and real data the efficiency of our CP method for state-of-the-art algorithms such as RankNet or LambdaMart.
title Transductive Conformal Inference for Full Ranking
topic Machine Learning
Methodology
url https://arxiv.org/abs/2501.11384