|国家预印本平台
首页|Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion

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

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

来源:Arxiv_logoArxiv
英文摘要

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.

Kang Zhou、Yuepei Li、Qiao Qiao、Qi Li

计算技术、计算机技术

Kang Zhou,Yuepei Li,Qiao Qiao,Qi Li.Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion[EB/OL].(2023-06-15)[2025-05-25].https://arxiv.org/abs/2306.09519.点此复制

评论