.png){kind=icon}
.png){kind=icon}
Return
MNS-EA: A Mixed Negative Sampling-Based Entity Alignment Model
.png){kind=icon}
PRE
AI
DOI：10.1007/978-981-95-5719-6_20.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Entity alignment is the process of identifying and linking entities (like people, organizations, or locations) across different datasets or knowledge bases that refer to the same real-world object. Most entity alignment methods suffer from noise introduced when incorporating multi-hop neighborhood information and the neglect of interactions involving negative entity pairs, leading to suboptimal alignment performance. To address these limitations, we propose a Mixed Negative Sampling-based Entity Alignment model (MNS-EA). The model initially embeds entities into a unified vector space through multilingual training, subsequently employs a single-layer network to integrate one-hop neighborhood information, and constructs negative samples via a hybrid negative sampling algorithm to mitigate erroneous matches under information scarcity. Comparative experiments conducted on three DBP15K subsets (zh_en, ja_en, fr_en) demonstrate that the proposed model significantly enhances alignment accuracy. On the fr_en dataset, the proposed model demonstrates particularly notable metric improvements: Hits@1 achieves a 5.1% absolute gain over the suboptimal model HGCN, while Hits@10 outperforms RNMthe second-best baselineby 3.3%. Furthermore, comprehensive experiments conducted on the DWY100K dataset systematically validate both the component-wise effectiveness of our framework and its cross-dataset generalization capability.
Keywords:
Knowledge Graph
Entity Alignment
Negative Samples
Mixed Negative Sampling
Multilingual Training
Journal
W
IF:
0
Papers:
32
Citations:
0