AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lu, Weigang, Guan, Ziyu, Zhao, Wei, Yang, Yaming
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913359759147008
author Lu, Weigang
Guan, Ziyu
Zhao, Wei
Yang, Yaming
author_facet Lu, Weigang
Guan, Ziyu
Zhao, Wei
Yang, Yaming
contents Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical industrial applications. In response, a new wave of methods, collectively known as GNN-to-MLP Knowledge Distillation, has emerged. They aim to transfer GNN-learned knowledge to a more efficient MLP student, which offers faster, resource-efficient inference while maintaining competitive performance compared to GNNs. However, these methods face significant challenges in situations with insufficient training data and incomplete test data, limiting their applicability in real-world applications. To address these challenges, we propose AdaGMLP, an AdaBoosting GNN-to-MLP Knowledge Distillation framework. It leverages an ensemble of diverse MLP students trained on different subsets of labeled nodes, addressing the issue of insufficient training data. Additionally, it incorporates a Node Alignment technique for robust predictions on test data with missing or incomplete features. Our experiments on seven benchmark datasets with different settings demonstrate that AdaGMLP outperforms existing G2M methods, making it suitable for a wide range of latency-sensitive real-world applications. We have submitted our code to the GitHub repository (https://github.com/WeigangLu/AdaGMLP-KDD24).
format Preprint
id arxiv_https___arxiv_org_abs_2405_14307
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation
Lu, Weigang
Guan, Ziyu
Zhao, Wei
Yang, Yaming
Machine Learning
Artificial Intelligence
Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical industrial applications. In response, a new wave of methods, collectively known as GNN-to-MLP Knowledge Distillation, has emerged. They aim to transfer GNN-learned knowledge to a more efficient MLP student, which offers faster, resource-efficient inference while maintaining competitive performance compared to GNNs. However, these methods face significant challenges in situations with insufficient training data and incomplete test data, limiting their applicability in real-world applications. To address these challenges, we propose AdaGMLP, an AdaBoosting GNN-to-MLP Knowledge Distillation framework. It leverages an ensemble of diverse MLP students trained on different subsets of labeled nodes, addressing the issue of insufficient training data. Additionally, it incorporates a Node Alignment technique for robust predictions on test data with missing or incomplete features. Our experiments on seven benchmark datasets with different settings demonstrate that AdaGMLP outperforms existing G2M methods, making it suitable for a wide range of latency-sensitive real-world applications. We have submitted our code to the GitHub repository (https://github.com/WeigangLu/AdaGMLP-KDD24).
title AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.14307