Meta Reasoning over Knowledge Graphs
This work addresses the practical problem of few-shot reasoning for knowledge graph applications, offering an incremental improvement over existing meta-learning methods.
The paper tackles few-shot knowledge graph reasoning by proposing a meta-learning framework that encodes task-specific meta information into initialization parameters, achieving better performance than MAML and other baselines on few-shot knowledge base completion benchmarks.
The ability to reason over learned knowledge is an innate ability for humans and humans can easily master new reasoning rules with only a few demonstrations. While most existing studies on knowledge graph (KG) reasoning assume enough training examples, we study the challenging and practical problem of few-shot knowledge graph reasoning under the paradigm of meta-learning. We propose a new meta learning framework that effectively utilizes the task-specific meta information such as local graph neighbors and reasoning paths in KGs. Specifically, we design a meta-encoder that encodes the meta information into task-specific initialization parameters for different tasks. This allows our reasoning module to have diverse starting points when learning to reason over different relations, which is expected to better fit the target task. On two few-shot knowledge base completion benchmarks, we show that the augmented task-specific meta-encoder yields much better initial point than MAML and outperforms several few-shot learning baselines.