Structure Aware Negative Sampling in Knowledge Graphs

TL;DR

This paper introduces SANS, a simple yet effective negative sampling method for knowledge graph embedding that leverages graph structure to generate meaningful negatives without complex optimization.

Contribution

It proposes Structure Aware Negative Sampling (SANS), a novel negative sampling strategy that uses graph structure to improve embedding quality without extra parameters.

Findings

SANS produces semantically meaningful negative samples.

SANS is competitive with state-of-the-art methods.

SANS requires no additional parameters or complex optimization.

Abstract

Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node's k-hop neighborhood. Empirically, we demonstrate that SANS finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization.