MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Tianjun, Sun, Jiaqi, Cao, Defu, Zhang, Kun, Chen, Guangyi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917708131467264
author Yao, Tianjun
Sun, Jiaqi
Cao, Defu
Zhang, Kun
Chen, Guangyi
author_facet Yao, Tianjun
Sun, Jiaqi
Cao, Defu
Zhang, Kun
Chen, Guangyi
contents Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frameworks are primarily designed for node classification within single graphs, leaving their applicability to graph classification largely unexplored. Two main challenges arise when extending KD for node classification to graph classification: (1) The inherent sparsity of learning signals due to soft labels being generated at the graph level; (2) The limited expressiveness of student MLPs, especially in datasets with limited input feature spaces. To overcome these challenges, we introduce MuGSI, a novel KD framework that employs Multi-granularity Structural Information for graph classification. Specifically, we propose multi-granularity distillation loss in MuGSI to tackle the first challenge. This loss function is composed of three distinct components: graph-level distillation, subgraph-level distillation, and node-level distillation. Each component targets a specific granularity of the graph structure, ensuring a comprehensive transfer of structural knowledge from the teacher model to the student model. To tackle the second challenge, MuGSI proposes to incorporate a node feature augmentation component, thereby enhancing the expressiveness of the student MLPs and making them more capable learners. We perform extensive experiments across a variety of datasets and different teacher/student model architectures. The experiment results demonstrate the effectiveness, efficiency, and robustness of MuGSI. Codes are publicly available at: \textbf{\url{https://github.com/tianyao-aka/MuGSI}.}
format Preprint
id arxiv_https___arxiv_org_abs_2406_19832
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
Yao, Tianjun
Sun, Jiaqi
Cao, Defu
Zhang, Kun
Chen, Guangyi
Machine Learning
I.2.6
Recent works have introduced GNN-to-MLP knowledge distillation (KD) frameworks to combine both GNN's superior performance and MLP's fast inference speed. However, existing KD frameworks are primarily designed for node classification within single graphs, leaving their applicability to graph classification largely unexplored. Two main challenges arise when extending KD for node classification to graph classification: (1) The inherent sparsity of learning signals due to soft labels being generated at the graph level; (2) The limited expressiveness of student MLPs, especially in datasets with limited input feature spaces. To overcome these challenges, we introduce MuGSI, a novel KD framework that employs Multi-granularity Structural Information for graph classification. Specifically, we propose multi-granularity distillation loss in MuGSI to tackle the first challenge. This loss function is composed of three distinct components: graph-level distillation, subgraph-level distillation, and node-level distillation. Each component targets a specific granularity of the graph structure, ensuring a comprehensive transfer of structural knowledge from the teacher model to the student model. To tackle the second challenge, MuGSI proposes to incorporate a node feature augmentation component, thereby enhancing the expressiveness of the student MLPs and making them more capable learners. We perform extensive experiments across a variety of datasets and different teacher/student model architectures. The experiment results demonstrate the effectiveness, efficiency, and robustness of MuGSI. Codes are publicly available at: \textbf{\url{https://github.com/tianyao-aka/MuGSI}.}
title MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
topic Machine Learning
I.2.6
url https://arxiv.org/abs/2406.19832