Knowledge Graph Completion by Intermediate Variables Regularization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Changyi, Cao, Yixin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909634988605440
author Xiao, Changyi
Cao, Yixin
author_facet Xiao, Changyi
Cao, Yixin
contents Knowledge graph completion (KGC) can be framed as a 3-order binary tensor completion task. Tensor decomposition-based (TDB) models have demonstrated strong performance in KGC. In this paper, we provide a summary of existing TDB models and derive a general form for them, serving as a foundation for further exploration of TDB models. Despite the expressiveness of TDB models, they are prone to overfitting. Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance. Therefore, we propose a novel regularization method for TDB models that addresses this limitation. The regularization is applicable to most TDB models and ensures tractable computation. Our method minimizes the norms of intermediate variables involved in the different ways of computing the predicted tensor. To support our regularization method, we provide a theoretical analysis that proves its effect in promoting low trace norm of the predicted tensor to reduce overfitting. Finally, we conduct experiments to verify the effectiveness of our regularization technique as well as the reliability of our theoretical analysis. The code is available at https://github.com/changyi7231/IVR.
format Preprint
id arxiv_https___arxiv_org_abs_2506_02749
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge Graph Completion by Intermediate Variables Regularization
Xiao, Changyi
Cao, Yixin
Machine Learning
Artificial Intelligence
Knowledge graph completion (KGC) can be framed as a 3-order binary tensor completion task. Tensor decomposition-based (TDB) models have demonstrated strong performance in KGC. In this paper, we provide a summary of existing TDB models and derive a general form for them, serving as a foundation for further exploration of TDB models. Despite the expressiveness of TDB models, they are prone to overfitting. Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance. Therefore, we propose a novel regularization method for TDB models that addresses this limitation. The regularization is applicable to most TDB models and ensures tractable computation. Our method minimizes the norms of intermediate variables involved in the different ways of computing the predicted tensor. To support our regularization method, we provide a theoretical analysis that proves its effect in promoting low trace norm of the predicted tensor to reduce overfitting. Finally, we conduct experiments to verify the effectiveness of our regularization technique as well as the reliability of our theoretical analysis. The code is available at https://github.com/changyi7231/IVR.
title Knowledge Graph Completion by Intermediate Variables Regularization
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.02749