Structure Aware Negative Sampling in Knowledge Graphs
This addresses the challenge of suboptimal negative sampling in knowledge graph completion for researchers and practitioners, though it is incremental as it builds on existing contrastive learning approaches.
The paper tackles the problem of generating hard negative samples for knowledge graph embedding by proposing Structure Aware Negative Sampling (SANS), which selects negatives from a node's k-hop neighborhood, resulting in competitive performance with state-of-the-art methods without extra parameters or adversarial optimization.
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.