Iterative Graph Self-Distillation

doi:10.1109/TKDE.2023.3303885

Iterative Graph Self-Distillation

2024-03-01

2

OA

AI

DOI：10.1109/TKDE.2023.3303885

Original

Original request for help

Save

Abstract

En 中文

Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distillation (IGSD) which learns graph-level representation in an unsupervised manner through instance discrimination using a self-supervised contrastive learning approach. IGSD involves a teacher-student distillation process that uses graph diffusion augmentations and constructs the teacher model using an exponential moving average of the student model. The intuition behind IGSD is to predict the teacher network representation of the graph pairs under different augmented views. As a natural extension, we also apply IGSD to semi-supervised scenarios by jointly regularizing the network with both supervised and self-supervised contrastive loss. Finally, we show that fine-tuning the IGSD-trained models with self-training can further improve graph representation learning. Empirically, we achieve significant and consistent performance gain on various graph datasets in both unsupervised and semi-supervised settings, which well validates the superiority of IGSD.

Keywords:

Task analysis

Representation learning

Kernel

Graph neural networks

Iterative methods

Data augmentation

Training

graph representation learning

self-supervised learning

Iterative Graph Self-Distillation

Abstract

Journal

Organization