Saved in:
Bibliographic Details
Main Authors: Abdolali, Maryam, Zakerian, Romina, Roshanfekr, Behnam, Ayar, Fardin, Rahmati, Mohammad
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.17842
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909549371326464
author Abdolali, Maryam
Zakerian, Romina
Roshanfekr, Behnam
Ayar, Fardin
Rahmati, Mohammad
author_facet Abdolali, Maryam
Zakerian, Romina
Roshanfekr, Behnam
Ayar, Fardin
Rahmati, Mohammad
contents In this paper, we propose a novel framework that combines ensemble learning with augmented graph structures to improve the performance and robustness of semi-supervised node classification in graphs. By creating multiple augmented views of the same graph, our approach harnesses the "wisdom of a diverse crowd", mitigating the challenges posed by noisy graph structures. Leveraging ensemble learning allows us to simultaneously achieve three key goals: adaptive confidence threshold selection based on model agreement, dynamic determination of the number of high-confidence samples for training, and robust extraction of pseudo-labels to mitigate confirmation bias. Our approach uniquely integrates adaptive ensemble consensus to flexibly guide pseudo-label extraction and sample selection, reducing the risks of error accumulation and improving robustness. Furthermore, the use of ensemble-driven consensus for pseudo-labeling captures subtle patterns that individual models often overlook, enabling the model to generalize better. Experiments on several real-world datasets demonstrate the effectiveness of our proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks
Abdolali, Maryam
Zakerian, Romina
Roshanfekr, Behnam
Ayar, Fardin
Rahmati, Mohammad
Machine Learning
Artificial Intelligence
In this paper, we propose a novel framework that combines ensemble learning with augmented graph structures to improve the performance and robustness of semi-supervised node classification in graphs. By creating multiple augmented views of the same graph, our approach harnesses the "wisdom of a diverse crowd", mitigating the challenges posed by noisy graph structures. Leveraging ensemble learning allows us to simultaneously achieve three key goals: adaptive confidence threshold selection based on model agreement, dynamic determination of the number of high-confidence samples for training, and robust extraction of pseudo-labels to mitigate confirmation bias. Our approach uniquely integrates adaptive ensemble consensus to flexibly guide pseudo-label extraction and sample selection, reducing the risks of error accumulation and improving robustness. Furthermore, the use of ensemble-driven consensus for pseudo-labeling captures subtle patterns that individual models often overlook, enabling the model to generalize better. Experiments on several real-world datasets demonstrate the effectiveness of our proposed method.
title Adapt, Agree, Aggregate: Semi-Supervised Ensemble Labeling for Graph Convolutional Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2503.17842