Few-Shot Semantic Relation Prediction Across Heterogeneous Graphs
Gespeichert in:
| Titel: | Few-Shot Semantic Relation Prediction Across Heterogeneous Graphs |
|---|---|
| Autoren: | Pengfei Ding, Yan Wang, Guanfeng Liu, Xiaofang Zhou |
| Quelle: | IEEE Transactions on Knowledge and Data Engineering. 35:10265-10280 |
| Publication Status: | Preprint |
| Verlagsinformationen: | Institute of Electrical and Electronics Engineers (IEEE), 2023. |
| Publikationsjahr: | 2023 |
| Schlagwörter: | FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Social networking (online), COVID-19, Mercury (metals), 02 engineering and technology, Graph neural networks, Semantics, Machine Learning (cs.LG), Heterogeneous graphs, Toy manufacturing industry, Artificial Intelligence (cs.AI), Meta-learning, Semantic relation prediction, 0202 electrical engineering, electronic engineering, information engineering, Companies |
| Beschreibung: | 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. |
| Publikationsart: | Article |
| ISSN: | 2326-3865 1041-4347 |
| DOI: | 10.1109/tkde.2023.3251951 |
| DOI: | 10.48550/arxiv.2207.05068 |
| Zugangs-URL: | http://arxiv.org/abs/2207.05068 |
| Rights: | IEEE Copyright arXiv Non-Exclusive Distribution |
| Dokumentencode: | edsair.doi.dedup.....62dead5613a7964d42ab332d5229fd9f |
| Datenbank: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | 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. |
|---|---|
| ISSN: | 23263865 10414347 |
| DOI: | 10.1109/tkde.2023.3251951 |