Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs
원문 초록
Real-world knowledge graphs are often characterized by low-frequency relations - a challenge that has prompted an increasing interest in few-shot link prediction methods. These methods perform link prediction for a set of new relations, unseen during training, given only a few example facts of each relation at test time. In this work, we perform a systematic study on a spectrum of models derived by generalizing the current state of the art for few-shot link prediction, with the goal of probing the limits of learning in this few-shot setting. We find that a simple zero-shot baseline - which ignores any relation-specific information - achieves surprisingly strong performance. Moreover, experiments on carefully crafted synthetic datasets show that having only a few examples of a relation fundamentally limits models from using fine-grained structural information and only allows for exploiting the coarse-grained positional information of entities. Together, our findings challenge the implicit assumptions and inductive biases of prior work and highlight new directions for research in this area.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EasySpider: A No-Code Visual System for Crawling the Web
Knowledge Graph Embedding via Graph Attenuated Attention Networks
Open-World Social Event Classification
Graph Collaborative Attention Network for Link Prediction in Knowledge Graphs
Demystifying Distributed Training of Graph Neural Networks for Link Prediction
Learnable Spatial-Temporal Positional Encoding for Link Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.