Saved in:
Bibliographic Details
Main Authors: Shen, Yutong, Xia, Ruizhe, Liu, Jingyi, Liu, Yinqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20736
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910157537017856
author Shen, Yutong
Xia, Ruizhe
Liu, Jingyi
Liu, Yinqi
author_facet Shen, Yutong
Xia, Ruizhe
Liu, Jingyi
Liu, Yinqi
contents Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by significant computational overhead and reliance on strong homophily assumptions. Traditional GNNs require expensive iterative training and multi-layer message passing, while existing training-free methods, such as Label Propagation, lack adaptability to heterophilo\-us graph structures. This paper presents \textbf{F$^2$LP-AP} (Fast and Flexible Label Propagation with Adaptive Propagation Kernel), a training-free, computationally efficient framework that adapts to local graph topology. Our method constructs robust class prototypes via the geometric median and dynamically adjusts propagation parameters based on the Local Clustering Coefficient (LCC), enabling effective modeling of both homophilous and heterophilous graphs without gradient-based training. Extensive experiments across diverse benchmark datasets demonstrate that \textbf{F$^2$LP-AP} achieves competitive or superior accuracy compared to trained GNNs, while significantly outperforming existing baselines in computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20736
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel
Shen, Yutong
Xia, Ruizhe
Liu, Jingyi
Liu, Yinqi
Machine Learning
Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by significant computational overhead and reliance on strong homophily assumptions. Traditional GNNs require expensive iterative training and multi-layer message passing, while existing training-free methods, such as Label Propagation, lack adaptability to heterophilo\-us graph structures. This paper presents \textbf{F$^2$LP-AP} (Fast and Flexible Label Propagation with Adaptive Propagation Kernel), a training-free, computationally efficient framework that adapts to local graph topology. Our method constructs robust class prototypes via the geometric median and dynamically adjusts propagation parameters based on the Local Clustering Coefficient (LCC), enabling effective modeling of both homophilous and heterophilous graphs without gradient-based training. Extensive experiments across diverse benchmark datasets demonstrate that \textbf{F$^2$LP-AP} achieves competitive or superior accuracy compared to trained GNNs, while significantly outperforming existing baselines in computational efficiency.
title F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel
topic Machine Learning
url https://arxiv.org/abs/2604.20736