Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion-猫眼课题宝

DOI：

10.1007/978-3-031-33380-4_8

发表时间：

2023-06

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Qiao Qiao-Qiao;Yuepei Li;Kang Zhou;Qi Li

少镜头知识图完成（FKGC）任务旨在预测与少镜头参考实体对的关系中的未知事实。目前的方法为每个参考实体对随机选择一个负样本以最小化基于边际的排名损失，如果负样本远离正样本然后超出边际，则容易导致零损失问题。此外，该实体在不同情况下应有不同的代表性。为了解决这些问题，我们提出了一种新的基于注意力损失的感知网络（RANA）框架。具体来说，为了更好地利用丰富的负样本和缓解零损失问题，我们有策略地选择相关的负样本，并设计了一个基于注意力的损失函数，以进一步区分每个负样本的重要性。直觉是，负样本与正样本更相似，对模型的贡献更大。此外，我们设计了一个动态的关系感知实体编码器学习上下文相关的实体表示。实验表明，RANA优于国家的最先进的模型在两个基准数据集。

Few-shot knowledge graph completion (FKGC) task aims to predict unseen facts of a relation with few-shot reference entity pairs. Current approaches randomly select one negative sample for each reference entity pair to minimize a margin-based ranking loss, which easily leads to a zero-loss problem if the negative sample is far away from the positive sample and then out of the margin. Moreover, the entity should have a different representation under a different context. To tackle these issues, we propose a novel Relation-Aware Network with Attention-Based Loss (RANA) framework. Specifically, to better utilize the plentiful negative samples and alleviate the zero-loss issue, we strategically select relevant negative samples and design an attention-based loss function to further differentiate the importance of each negative sample. The intuition is that negative samples more similar to positive samples will contribute more to the model. Further, we design a dynamic relation-aware entity encoder for learning a context-dependent entity representation. Experiments demonstrate that RANA outperforms the state-of-the-art models on two benchmark datasets.

Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion

文献摘要

相似文献