Model-based Subsampling for Knowledge Graph Completion

2023-09-17 · Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

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.

📄 PDF Abstract BibTeX arXiv:2309.09296

Code (1)

xincanfeng/ms_kge 공식 구현 pytorch

Tasks

Graph Embedding Knowledge Graph Completion Knowledge Graph Embeddingmodel

Methods 이 논문이 사용한 방법론

MBS To avoid the problem caused by low-frequent entity-relation pairs, our MBS uses the estimated probabilities from a trained model $\mathbf{\theta}'$ to calculate frequencies for…

Self-Adversarial Negative Sampling 설명 없음

RotatE RotatE is a method for generating graph embeddings which is able to model and infer various relation patterns including: symmetry/antisymmetry, inversion, and composition.…

TransE TransE is an energy-based model that produces knowledge base embeddings. It models relationships by interpreting them as translations operating on the low-dimensional…

Subsampling for Knowledge Graph Embedding Explained

2022-09-13 · Hidetaka Kamigaito, Katsuhiko Hayashi

In this article, we explain the recent advance of subsampling methods in knowledge graph embedding (KGE) starting from the original one used in word2vec.

Graph Embedding Knowledge Graph Embedding

Subsampling Graphs with GNN Performance Guarantees

2025-02-23 · Mika Sarkin Jain, Stefanie Jegelka, Ishani Karmarkar, Luana Ruiz 외

How can we subsample graph data so that a graph neural network (GNN) trained on the subsample achieves performance comparable to training on the full dataset? This question is of fundamental interest, as smaller datasets…

Graph Neural Network Model Selection

A divide-and-conquer algorithm for binary matrix completion

2019-07-09 · Melanie Beckerleg, Andrew Thompson

We propose an algorithm for low rank matrix completion for matrices with binary entries which obtains explicit binary factors. Our algorithm, which we call TBMC (\emph{Tiling for Binary Matrix Completion}), gives interpr…

Low-Rank Matrix Completion Matrix Completion Recommendation Systems

Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding

2024-07-05 · Xincan Feng, Hidetaka Kamigaito, Katsuhiko Hayashi, Taro Watanabe

Knowledge Graphs (KGs) are fundamental resources in knowledge-intensive tasks in NLP. Due to the limitation of manually creating KGs, KG Completion (KGC) has an important role in automatically completing KGs by scoring t…

Graph Embedding Knowledge Graph Embedding Knowledge Graphs Triplet

Fast Knowledge Graph Completion using Graphics Processing Units

2023-07-22 · Chun-Hee Lee, Dong-oh Kang, Hwa Jeon Song

Knowledge graphs can be used in many areas related to data semantics such as question-answering systems, knowledge based systems. However, the currently constructed knowledge graphs need to be complemented for better kno…

Graph Embedding Knowledge Graph Completion Knowledge Graph Embedding Knowledge Graphs+1