arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.11355cs.LGcs.CLstat.ML
收藏

知识图谱中的结构感知负采样

Structure Aware Negative Sampling in Knowledge Graphs

McGill University(麦吉尔大学);Montreal Institute of Learning Algorithms (Mila)(蒙特利尔学习算法研究所(米拉))

Kian Ahrabian, Aarash Feizi, Yasmin Salehi, William L. Hamilton, Avishek Joey Bose

摘要:

使用对比估计学习知识图谱中的实体和关系的低维表示代表了用于推断连接模式的可扩展且有效的方法。对比学习方法的一个关键方面是选择产生硬负样本的腐败分布,这迫使嵌入模型学习判别表示并找到观察数据的关键特征。虽然早期的方法要么采用过于简单的腐败分布,即均匀的,容易产生无信息的否定或复杂的对抗性分布具有挑战性的优化方案,但它们没有明确地结合已知的图形结构,导致次优否定。在本文中,我们提出了结构感知负采样(SANS),一个廉价的负采样策略,利用丰富的图形结构,从节点的k跳邻域选择负样本。从经验上讲,我们证明了SANS发现语义上有意义的负面影响,并与SOTA方法竞争,同时不需要额外的参数,也不需要困难的对抗性优化。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑