Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion
This work addresses a specific bottleneck in few-shot learning for knowledge graphs, offering incremental improvements over existing methods.
The paper tackles the few-shot knowledge graph completion problem by proposing a Relation-Aware Network with Attention-Based Loss (RANA) framework to address zero-loss issues and improve entity representation, achieving state-of-the-art results on two benchmark datasets.
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.