File(s) under permanent embargo
Entity similarity-based negative sampling for knowledge graph embedding
conference contributionposted on 2023-05-23, 15:32 authored by Naimeng YaoNaimeng Yao, Liu, Q, Xiang LiXiang Li, Yang, Y, Quan BaiQuan Bai
Knowledge graph embedding (KGE) models optimize loss functions to maximize the total plausibility of positive triples and minimize the plausibility of negative triples. Negative samples are essential in KGE training since they are not as observable as positive samples. Currently, most negative sampling methods apply different techniques to keep track of negative samples with high scores that are regarded as quality negative samples. While, we found entities with similar semantic contexts are easier to be deceptive and misclassified, contributing to quality negative samples. This is not considered in most negative sampling approaches. Besides, the unequal effectiveness of quality negative samples in different loss functions is usually ignored. In this paper, we propose an Entity Similarity-based Negative Sampling framework (ESNS). The framework takes semantic similarities among entities into consideration with a shift-based logistic loss function. Comprehensive experiments on the five benchmark datasets have been conducted, and the experimental results demonstrate that ESNS outperforms the state-of-the-art negative sampling methods in the link prediction task.
Publication titlePRICAI 2022: Trends in Artificial Intelligence Proceedings, Part II
EditorsS Khanna et al.
Department/SchoolSchool of Information and Communication Technology
Place of publicationSwitzerland
Event title19th Pacific Rim International Conference on Artificial Intelligence PRICAI 2022,
Event VenueShanghai, China