Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
Graph Neural Networks (GNNs) have been generalized to process the heterogeneous graphs by various approaches. Unfortunately, these approaches usually model the heterogeneity via various complicated modules. This paper aims to propose a simple yet effective framework to assign adequate ability to the homogeneous GNNs to handle the heterogeneous graphs. Specifically, we propose Relation Embedding based Graph Neural Network (RE-GNN), which employs only one parameter per relation to embed the importance of distinct types of relations and node-type-specific self-loop connections. To optimize these relation embeddings and the model parameters simultaneously, a gradient scaling factor is proposed to constrain the embeddings to converge to suitable values. Besides, we interpret the proposed RE-GNN from two perspectives, and theoretically demonstrate that our RE-GCN possesses more expressive power than GTN (which is a typical heterogeneous GNN, and it can generate meta-paths adaptively). Extensive experiments demonstrate that our RE-GNN can effectively and efficiently handle the heterogeneous graphs and can be applied to various homogeneous GNNs.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph LearningGraph Neural NetworkNode ClassificationRelationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literature has revealed the limitations of comm…
Node ClassificationRepresentation LearningHeterogeneous Graph Transformer
Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types…
Graph SamplingHeterogeneous Node ClassificationNode Property PredictionHGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised fra…
Graph Representation LearningPrompt LearningRepresentation LearningAutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and h…
Neural Architecture SearchHop-Hop Relation-aware Graph Neural Networks
Graph Neural Networks (GNNs) are widely used in graph representation learning. However, most GNN methods are designed for either homogeneous or heterogeneous graphs. In this paper, we propose a new model, Hop-Hop Relatio…
Graph EmbeddingGraph Neural NetworkGraph Representation LearningKnowledge Graph Embedding+2