Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
arXiv:1906.05489
Abstract
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose CogKR for one-shot KG reasoning. The one-shot relational learning problem is tackled through two modules: the summary module summarizes the underlying relationship of the given instances, based on which the reasoning module infers the correct answers. Motivated by the dual process theory in cognitive science, in the reasoning module, a cognitive graph is built by iteratively coordinating retrieval (System 1, collecting relevant evidence intuitively) and reasoning (System 2, conducting relational reasoning over collected information). The structural information offered by the cognitive graph enables our model to aggregate pieces of evidence from multiple reasoning paths and explain the reasoning process graphically. Experiments show that CogKR substantially outperforms previous state-of-the-art models on one-shot KG reasoning benchmarks, with relative improvements of 24.3%-29.7% on MRR. The source code is available at https://github.com/THUDM/CogKR.
References in corpus (7)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
- Hypernetwork Knowledge Graph Embeddings
- M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
- Knowledge Graph Completion via Complex Tensor Factorization
- Cognitive Graph for Multi-Hop Reading Comprehension at Scale
Cited by in corpus (5)
- Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
- What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
- Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
- One-shot Learning for Temporal Knowledge Graphs
- Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion