.png){kind=icon}
Return
A knowledge graph embedding model based on multi-level analogical reasoning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10586-024-04514-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The existing knowledge graph embedding (KGE) models based on graph neural networks (GNNs) typically aggregate unreliable neighboring node information, leading to a decrease in the accuracy of inference results. Additionally, incomplete triples commonly found in knowledge graphs(KGs) pose challenges for KGE models to conduct inductive reasoning. To address these issues, this paper proposes a KGE model named MAKE, which is based on GNN and multi-level analogical reasoning. MAKE model features include: (1) Utilization of multi-level semantic information: MAKE explicitly models semantic information at the levels of relations, entities, and triples using GNN. Through multi-level aggregation, it effectively combines semantic information to generate original aggregated representations, balancing the noise impact from neighbors and enhancing model robustness. (2) Multi-level analogical reasoning: MAKE introduces analogical reasoning methods at the aforementioned levels to generate analogical aggregated representations, thus compensating for the limitations of inductive reasoning. (3) Integration of inductive and analogical reasoning capabilities: By concatenating two representations using a transformation matrix, MAKE produces the final aggregated representation of semantic information, enabling the model to conduct inference more effectively. Extensive experiments demonstrate that MAKE outperforms all baseline models significantly on the FB15K-237 and WN18RR datasets. Particularly noteworthy is its performance on the complex dataset FB15K-237, where MAKE surpasses baseline values by 1 and 2.3% on the MRR and Hits@1 metrics, respectively.
Keywords:
Knowledge graph embedding (KGE)
Graph neural network (GNN)
Analogical reasoning
Semantic information aggregation
Journal
C
IF:
4.1
Papers:
5.0K
Citations:
7.5K
Organization
Cited Papers
I Know What You Want to Express: Sentence Element Inference by Incorporating External Knowledge Base
PREAI
ShareSave
High antibody responses in rabbits immunized with influenza virus ISCOMs containing a repeated sequence of the Plasmodium falciparum antigen Pf155/RESA.png)
Vaccine
VaccineIF0
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSave
View more