Graph Meta Learning via Local Subgraphs

Abstract

Prevailing methods for graphs require abundant label and edge information for learning. When data for a new task are scarce, meta-learning can learn from prior experiences and form much-needed inductive biases for fast adaption to new tasks. Here, we introduce G-Meta, a novel meta-learning algorithm for graphs. G-Meta uses local subgraphs to transfer subgraph-specific information and learn transferable knowledge faster via meta gradients. G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets. G-Meta is theoretically justified as we show that the evidence for a prediction can be found in the local subgraph surrounding the target node or edge. Experiments on seven datasets and nine baseline methods show that G-Meta outperforms existing methods by up to 16.3%. Unlike previous methods, G-Meta successfully learns in challenging, few-shot learning settings that require generalization to completely new graphs and never-before-seen labels. Finally, G-Meta scales to large graphs, which we demonstrate on a new Tree-of-Life dataset comprising of 1,840 graphs, a two-orders of magnitude increase in the number of graphs used in prior work.

arXiv commentNeurIPS 2020

References in corpus (21)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Modeling polypharmacy side effects with graph convolutional networks
• Theoretical Models of Learning to Learn
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Matching Networks for One Shot Learning
• Variational Graph Auto-Encoders
• Biological network comparison using graphlet degree distribution
• Predicting multicellular function through multi-layer tissue networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Learning Structural Node Embeddings Via Diffusion Wavelets
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Learning to Propagate for Graph Meta-Learning
• Neural Subgraph Matching
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
• Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs

Cited by in corpus (2)

• Data Considerations in Graph Representation Learning for Supply Chain Networks
• Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results