MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification
Document Type
Conference Proceeding
Publication Title
WWW 2024 - Proceedings of the ACM Web Conference
Abstract
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: https://github.com/tianyao-aka/MuGSI.
First Page
709
Last Page
720
DOI
10.1145/3589334.3645542
Publication Date
5-13-2024
Keywords
graph classification, graph neural networks, knowledge distillation
Recommended Citation
T. Yao et al., "MuGSI: Distilling GNNs with Multi-Granularity Structural Information for Graph Classification," WWW 2024 - Proceedings of the ACM Web Conference, pp. 709 - 720, May 2024.
The definitive version is available at https://doi.org/10.1145/3589334.3645542