Generalized Few-Shot Node Classification
Authors:
- 1 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 608-617
Abstract
For real-world graph data, the node class distribution is inherently imbalanced and long-tailed, which naturally leads to a few-shot learning scenario with limited nodes labeled for newly emerging classes. Existing efforts are carefully designed to solve such a few-shot learning problem via data augmentation, learning transferable initialization, to name a few. However, most, if not all, of them are based on a strong assumption that all the test nodes must exclusively come from novel classes, which is impractical in real-world applications. In this paper, we study a broader and more realistic problem named generalized few-shot node classification, where the test samples can be from both novel classes and base classes. Compared with the standard fewshot node classification, this new problem imposes several unique challenges, including asymmetric classification and inconsistent preference. To counter those challenges, we propose a shot-aware graph neural network (STAGER) equipped with an uncertainty-based weight assigner module for adaptive propagation. To formulate this problem from the meta-learning perspective, we propose a new training paradigm named imbalanced episodic training to ensure the label distribution is consistent between the training and test scenarios. Experiment results on four real-world datasets demonstrate the efficacy of our model, with up to 14% accuracy improvement over baselines.Keywords
This publication has 27 references indexed in Scilit:
- Multi-modal Cycle-Consistent Generalized Zero-Shot Learning2018
- Dynamic Few-Shot Visual Learning Without Forgetting2018
- An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild2016
- Node Classification in Signed Social Networks2016
- Inferring Networks of Substitutable and Complementary Products2015
- On Node Classification in Dynamic Content-based Networks2011
- Node Classification in Social Networks2011
- ArnetMiner2008
- Lifelong Learning Algorithms1998
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989