Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Maneriker, Pranav, Vadlamani, Aditya T., Srinivasan, Anutam, He, Yuntian, Payani, Ali, Parthasarathy, Srinivasan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.18332
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918025397010432
author Maneriker, Pranav
Vadlamani, Aditya T.
Srinivasan, Anutam
He, Yuntian
Payani, Ali
Parthasarathy, Srinivasan
author_facet Maneriker, Pranav
Vadlamani, Aditya T.
Srinivasan, Anutam
He, Yuntian
Payani, Ali
Parthasarathy, Srinivasan
contents Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The nascent nature of these explorations has led to conflicting choices for implementations, baselines, and method evaluation. In this work, we analyze the design choices made in the literature and discuss the tradeoffs associated with existing methods. Building on the existing implementations, we introduce techniques to scale existing methods to large-scale graph datasets without sacrificing performance. Our theoretical and empirical results justify our recommendations for future scholarship in graph conformal prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18332
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
Maneriker, Pranav
Vadlamani, Aditya T.
Srinivasan, Anutam
He, Yuntian
Payani, Ali
Parthasarathy, Srinivasan
Machine Learning
Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The nascent nature of these explorations has led to conflicting choices for implementations, baselines, and method evaluation. In this work, we analyze the design choices made in the literature and discuss the tradeoffs associated with existing methods. Building on the existing implementations, we introduce techniques to scale existing methods to large-scale graph datasets without sacrificing performance. Our theoretical and empirical results justify our recommendations for future scholarship in graph conformal prediction.
title Conformal Prediction: A Theoretical Note and Benchmarking Transductive Node Classification in Graphs
topic Machine Learning
url https://arxiv.org/abs/2409.18332