Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
arXiv:2103.03547
Abstract
Graph classification is a highly impactful task that plays a crucial role in a myriad of real-world applications such as molecular property prediction and protein function prediction.Aiming to handle the new classes with limited labeled graphs, few-shot graph classification has become a bridge of existing graph classification solutions and practical usage.This work explores the potential of metric-based meta-learning for solving few-shot graph classification.We highlight the importance of considering structural characteristics in the solution and propose a novel framework which explicitly considers global structure and local structure of the input graph. An implementation upon GIN, named SMF-GIN, is tested on two datasets, Chembl and TRIANGLES, where extensive experiments validate the effectiveness of the proposed method. The Chembl is constructed to fill in the gap of lacking large-scale benchmark for few-shot graph classification evaluation, which is released together with the implementation of SMF-GIN at: https://github.com/jiangshunyu/SMF-GIN.
arXiv commentAI Open Journal Volume 2, 2021, Pages 160-167
References in corpus (7)
- Semi-Supervised Classification with Graph Convolutional Networks
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Inductive Representation Learning on Large Graphs
- SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
- MoleculeNet: A Benchmark for Molecular Machine Learning
- Meta-Graph: Few Shot Link Prediction via Meta Learning