Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
arXiv:2007.02914
Abstract
We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users in online social networks. To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} provides each node a latent representation according to the graph structure. (2) A \emph{meta-learning module} captures the relationships between the graph structure and the node labels as prior knowledge in a meta-learning manner. Additionally, we introduce an \emph{embedding transformation function} that remedies the deficiency of the straightforward use of meta-learning. Inherently, the meta-learned prior knowledge can be used to facilitate the learning of few-shot novel labels. (3) An \emph{optimization module} employs a simple yet effective scheduling strategy to train the above two modules with a balance between graph structure learning and meta-learning. Experiments on four real-world datasets show that MetaTNE brings a huge improvement over the state-of-the-art methods.
arXiv commentAccepted to NeurIPS 2020
References in corpus (15)
- Distributed Representations of Words and Phrases and their Compositionality
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Inductive Representation Learning on Large Graphs
- struc2vec: Learning Node Representations from Structural Identity
- Tune: A Research Platform for Distributed Model Selection and Training
- Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning
- Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations
- Strategies for Pre-training Graph Neural Networks
- MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
- Learning to Propagate for Graph Meta-Learning
- Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
- Automated Relational Meta-learning
- Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
- Few-Shot Knowledge Graph Completion