Learning to Propagate for Graph Meta-Learning

Abstract

Meta-learning extracts common knowledge from learning different tasks and uses it for unseen tasks. It can significantly improve tasks that suffer from insufficient training data, e.g., few shot learning. In most meta-learning methods, tasks are implicitly related by sharing parameters or optimizer. In this paper, we show that a meta-learner that explicitly relates tasks on a graph describing the relations of their output dimensions (e.g., classes) can significantly improve few shot learning. The graph's structure is usually free or cheap to obtain but has rarely been explored in previous works. We develop a novel meta-learner of this type for prototype-based classification, in which a prototype is generated for each class, such that the nearest neighbor search among the prototypes produces an accurate classification. The meta-learner, called "Gated Propagation Network (GPN)", learns to propagate messages between prototypes of different classes on the graph, so that learning the prototype of each class benefits from the data of other related classes. In GPN, an attention mechanism aggregates messages from neighboring classes of each class, with a gate choosing between the aggregated message and the message from the class itself. We train GPN on a sequence of tasks from many-shot to few shot generated by subgraph sampling. During training, it is able to reuse and update previously achieved prototypes from the memory in a life-long learning cycle. In experiments, under different training-test discrepancy and test task generation settings, GPN outperforms recent meta-learning methods on two benchmark datasets. The code of GPN and dataset generation is available at https://github.com/liulu112601/Gated-Propagation-Net.

Accepted to NeurIPS 2019, code at https://github.com/liulu112601/Gated-Propagation-Net, slides at https://liulu112601.github.io/resources/GPN-NeurIPS-Slides-revised.pdf, Poster at https://liulu112601.github.io/resources/Graph-Meta-Learning-Poster-revised.pdf

Cited by in corpus (20)

• Graph Neural Network for Traffic Forecasting: A Survey
• Free Lunch for Few-shot Learning: Distribution Calibration
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
• Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Graph Meta Learning via Local Subgraphs
• Isometric Propagation Network for Generalized Zero-shot Learning
• Attribute Propagation Network for Graph Zero-shot Learning
• Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• Concept Learners for Few-Shot Learning
• Hierarchical Protein Function Prediction with Tail-GNNs
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
• Model-Agnostic Graph Regularization for Few-Shot Learning
• Interpretable Time-series Classification on Few-shot Samples
• Confusable Learning for Large-class Few-Shot Classification