Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)
This work addresses the problem of inferring facts with limited data for researchers in knowledge graph completion, but it is incremental as it builds on existing metric-learning methods by adding entity interaction modeling.
The paper tackles few-shot relation learning by proposing TransAM, a model that captures entity interactions within and between triples using a transformer with local-global attention, achieving effectiveness on NELL-One and Wiki-One datasets in 1-shot settings.
Few-shot relation learning refers to infer facts for relations with a limited number of observed triples. Existing metric-learning methods for this problem mostly neglect entity interactions within and between triples. In this paper, we explore this kind of fine-grained semantic meanings and propose our model TransAM. Specifically, we serialize reference entities and query entities into sequence and apply transformer structure with local-global attention to capture both intra- and inter-triple entity interactions. Experiments on two public benchmark datasets NELL-One and Wiki-One with 1-shot setting prove the effectiveness of TransAM.