Stay Positive: Knowledge Graph Embedding Without Negative Sampling
Knowledge graphs (KGs) are typically incomplete and we often wish to infer new facts given the existing ones. This can be thought of as a binary classification problem; we aim to predict if new facts are true or false. Unfortunately, we generally only have positive examples (the known facts) but we also need negative ones to train a classifier. To resolve this, it is usual to generate negative examples using a negative sampling strategy. However, this can produce false negatives which may reduce performance, is computationally expensive, and does not produce calibrated classification probabilities. In this paper, we propose a training procedure that obviates the need for negative sampling by adding a novel regularization term to the loss function. Our results for two relational embedding models (DistMult and SimplE) show the merit of our proposal both in terms of performance and speed.
Code (1)
Tasks
Binary ClassificationGraph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsSimilar Papers 제목 키워드 기반
zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
Modeling evolving knowledge over temporal knowledge graphs (TKGs) has become a heated topic. Various methods have been proposed to forecast links on TKGs. Most of them are embedding-based, where hidden representations ar…
Knowledge GraphsRelationRelational Reasoning$μ\text{KG}$: A Library for Multi-source Knowledge Graph Embeddings and Applications
This paper presents $\mu\text{KG}$, an open-source Python library for representation learning over knowledge graphs. $\mu\text{KG}$ supports joint representation learning over multi-source knowledge graphs (and also a si…
Entity AlignmentEntity TypingGPUGraph Embedding+7Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs
Knowledge graphs are large, useful, but incomplete knowledge repositories. They encode knowledge through entities and relations which define each other through the connective structure of the graph. This has inspired met…
Knowledge Graph EmbeddingsKnowledge GraphsLink PredictionUpdating Embeddings for Dynamic Knowledge Graphs
Data in Knowledge Graphs often represents part of the current state of the real world. Thus, to stay up-to-date the graph data needs to be updated frequently. To utilize information from Knowledge Graphs, many state-of-t…
Knowledge GraphsLink PredictionKnowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting Strategy
Knowledge graph embedding aims to represent entities and relations as low-dimensional vectors, which is an effective way for predicting missing links in knowledge graphs. Designing a strong and effective loss framework i…
Graph EmbeddingKnowledge Graph EmbeddingKnowledge GraphsLink Prediction+1