Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Xiaotian, Zeng, Hanqing, Chen, Yu, Nie, Shaoliang, Liu, Jingzhou, Narang, Kanika, Shakeri, Zahra, Sankararaman, Karthik Abinav, Jiang, Song, Khabsa, Madian, Wang, Qifan, Hu, Xia
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2310.00183
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912023392026624
author Han, Xiaotian
Zeng, Hanqing
Chen, Yu
Nie, Shaoliang
Liu, Jingzhou
Narang, Kanika
Shakeri, Zahra
Sankararaman, Karthik Abinav
Jiang, Song
Khabsa, Madian
Wang, Qifan
Hu, Xia
author_facet Han, Xiaotian
Zeng, Hanqing
Chen, Yu
Nie, Shaoliang
Liu, Jingzhou
Narang, Kanika
Shakeri, Zahra
Sankararaman, Karthik Abinav
Jiang, Song
Khabsa, Madian
Wang, Qifan
Hu, Xia
contents This paper investigates the relationship between graph convolution and Mixup techniques. Graph convolution in a graph neural network involves aggregating features from neighboring samples to learn representative features for a specific node or sample. On the other hand, Mixup is a data augmentation technique that generates new examples by averaging features and one-hot labels from multiple samples. One commonality between these techniques is their utilization of information from multiple samples to derive feature representation. This study aims to explore whether a connection exists between these two approaches. Our investigation reveals that, under two mild conditions, graph convolution can be viewed as a specialized form of Mixup that is applied during both the training and testing phases. The two conditions are: 1) \textit{Homophily Relabel} - assigning the target node's label to all its neighbors, and 2) \textit{Test-Time Mixup} - Mixup the feature during the test time. We establish this equivalence mathematically by demonstrating that graph convolution networks (GCN) and simplified graph convolution (SGC) can be expressed as a form of Mixup. We also empirically verify the equivalence by training an MLP using the two conditions to achieve comparable performance.
format Preprint
id arxiv_https___arxiv_org_abs_2310_00183
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Equivalence of Graph Convolution and Mixup
Han, Xiaotian
Zeng, Hanqing
Chen, Yu
Nie, Shaoliang
Liu, Jingzhou
Narang, Kanika
Shakeri, Zahra
Sankararaman, Karthik Abinav
Jiang, Song
Khabsa, Madian
Wang, Qifan
Hu, Xia
Machine Learning
Artificial Intelligence
This paper investigates the relationship between graph convolution and Mixup techniques. Graph convolution in a graph neural network involves aggregating features from neighboring samples to learn representative features for a specific node or sample. On the other hand, Mixup is a data augmentation technique that generates new examples by averaging features and one-hot labels from multiple samples. One commonality between these techniques is their utilization of information from multiple samples to derive feature representation. This study aims to explore whether a connection exists between these two approaches. Our investigation reveals that, under two mild conditions, graph convolution can be viewed as a specialized form of Mixup that is applied during both the training and testing phases. The two conditions are: 1) \textit{Homophily Relabel} - assigning the target node's label to all its neighbors, and 2) \textit{Test-Time Mixup} - Mixup the feature during the test time. We establish this equivalence mathematically by demonstrating that graph convolution networks (GCN) and simplified graph convolution (SGC) can be expressed as a form of Mixup. We also empirically verify the equivalence by training an MLP using the two conditions to achieve comparable performance.
title On the Equivalence of Graph Convolution and Mixup
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2310.00183