Few-Shot Semantic Relation Prediction across Heterogeneous Graphs

TL;DR

This paper introduces MetaGS, a meta-learning based graph neural network that effectively predicts new semantic relations across heterogeneous graphs with limited labeled data, outperforming existing methods.

Contribution

The paper proposes MetaGS, a novel approach combining subgraph decomposition, two-view GNNs, and hyper-prototypical networks for few-shot semantic relation prediction across multiple heterogeneous graphs.

Findings

MetaGS outperforms state-of-the-art methods on three real-world datasets.

Effective learning from few labeled samples in heterogeneous graph scenarios.

Demonstrates robustness across different types of semantic relations.

Abstract

Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types of objects and different types of links. In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data. Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with few labeled data. This inspires a novel problem of few-shot semantic relation prediction across heterogeneous graphs. However, the existing methods cannot solve this problem because they not only require a large number of labeled samples as input, but also focus on a single graph with a fixed heterogeneity. Targeting this novel and challenging problem, in this paper, we propose a Meta-learning based Graph neural network for Semantic relation prediction, named MetaGS. Firstly, MetaGS decomposes the graph structure between objects into multiple normalized subgraphs, then adopts a two-view graph neural network to capture local heterogeneous information and global structure information of these subgraphs. Secondly, MetaGS aggregates the information of these subgraphs with a hyper-prototypical network, which can learn from existing semantic relations and adapt to new semantic relations. Thirdly, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation of few labeled data. Extensive experiments on three real-world datasets have demonstrated the superior performance of MetaGS over the state-of-the-art methods.