Model-based Subsampling for Knowledge Graph Completion

Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe
9/17/2023
cs.CLcs.AIcs.LG

Official code: xincanfeng/ms_kge (4 stars, MIT, last commit 2024-06-30).

Abstract

Subsampling is effective in Knowledge Graph Embedding (KGE) for reducing overfitting caused by the sparsity in Knowledge Graph (KG) datasets. However, current subsampling approaches consider only frequencies of queries that consist of entities and their relations. Thus, the existing subsampling potentially underestimates the appearance probabilities of infrequent queries even if the frequencies of their entities or relations are high. To address this problem, we propose Model-based Subsampling (MBS) and Mixed Subsampling (MIX) to estimate their appearance probabilities through predictions of KGE models. Evaluation results on datasets FB15k-237, WN18RR, and YAGO3-10 showed that our proposed subsampling methods actually improved the KG completion performances for popular KGE models, RotatE, TransE, HAKE, ComplEx, and DistMult.

View on arXivView PDF

Code Implementations(1)

xincanfeng/ms_kgeOfficial100%
MIT

model-based subsampling

40Shell, PythonJul 25, 20222 years agoMIT

Similar Papers

On Large-scale Evaluation of Embedding Models for Knowledge Graph Completion

82% match2025

Breaking Rank Bottlenecks in Knowledge Graph Embeddings

82% match2025

DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion

82% match1 repo62023

Robust Knowledge Graph Embedding via Denoising

81% match2025

IntelliGraphs: Datasets for Benchmarking Knowledge Graph Generation

81% match1 repo252023

Toward Degree Bias in Embedding-Based Knowledge Graph Completion

80% match1 repo152023

Cite this paper

@article{feng2023modelbased,
  title  = {Model-based Subsampling for Knowledge Graph Completion},
  author = {Xincan Feng and Hidetaka Kamigaito and Katsuhiko Hayashi and Taro Watanabe},
  year   = {2023},
  eprint = {2309.09296},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.09296v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.09296.svg)](https://codeofpaper.com/paper/2309.09296)

Discussion