Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
Open Access
- 24 October 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (9) , 1-30
Abstract
Node classification is an essential problem in graph learning. However, many models typically obtain unsatisfactory performance when applied to few-shot scenarios. Some studies have attempted to combine meta-learning with graph neural networks to solve few-shot node classification on graphs. Despite their promising performance, some limitations remain. First, they employ the node encoding mechanism of homophilic graphs to learn node embeddings, even in heterophilic graphs. Second, existing models based on meta-learning ignore the interference of randomness in the learning process. Third, they are trained using only limited labeled nodes within the specific task, without explicitly utilizing numerous unlabeled nodes. Finally, they treat almost all sampled tasks equally without customizing them for their uniqueness. To address these issues, we propose a novel framework for few-shot node classification called Meta-GPS \(++\) . Specifically, we first adopt an efficient method to learn discriminative node representations on homophilic and heterophilic graphs. Then, we leverage a prototype-based approach to initialize parameters and contrastive learning for regularizing the distribution of node embeddings. Moreover, we apply self-training to extract valuable information from unlabeled nodes. Additionally, we adopt S \({}^{2}\) (scaling and shifting) transformation to learn transferable knowledge from diverse tasks. The results on real-world datasets show the superiority of Meta-GPS \(++\) . Our code is available here .
Keywords
All Related Versions
Funding Information
- National Key Research and Development Program of China (2021YFF1201200)
- National Natural Science Foundation of China (62172187, 62372494, and 62372209)
- Guangdong Universities’ Innovation Team Project (2021KCXTD015)
- Guangdong Key Disciplines Project (2021ZDJS138 and 2022ZDJS139)
- Fausto Giunchiglia’s work is funded by European Union’s Horizon 2020 FET Proactive project (823783)
This publication has 46 references indexed in Scilit:
- Time-Aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question Answering2023
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- A Comprehensive Survey on Graph Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 2020
- Compound Memory Networks for Few-Shot Video Classification2018
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Memory Matching Networks for One-Shot Image Recognition2018
- Latent feature learning in social media network2013
- ArnetMiner2008
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- A Cluster Separation MeasureIEEE Transactions on Pattern Analysis and Machine Intelligence, 1979