Knowledge Base Embedding for Sampling-Based Prediction

doi:10.1145/3533769

Knowledge Base Embedding for Sampling-Based Prediction

2023-04-08

1

PRE

AI

DOI：10.1145/3533769

Original request for help

Save

Abstract

En 中文

Each link prediction task requires different degrees of answer diversity. While a link prediction task may expect up to a couple of answers, another may expect nearly a hundred answers. Given this fact, the performance of a link prediction model can be estimated more accurately if a flexible number of obtained answers are estimated instead of a predefined number of answers. Inspired by this, in this article, we analyze two evaluation criteria for link prediction tasks, respectively ranking-based protocol and sampling-based protocol. Furthermore, we study two classes of models on link prediction task, direct model and latent-variable model respectively, to demonstrate that latent-variable model performs better under the sampling-based protocol. We then propose a latent-variable model where the framework of Conditional Variational AutoEncoder (CVAE) is applied. Experimental study suggests that the proposed model performs comparably to the current state-of-the-art even under the conventional rank-based protocol. Under the sampling-based protocol, the proposed model is shown to outperform various state-of-the-art models.

Keywords:

Link prediction

Knowledge Base Embedding

Conditional Variational AutoEncoder

Knowledge Base Embedding for Sampling-Based Prediction

Abstract

Journal

Organization