Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion

Abstract

Knowledge graphs (KGs), as a structured form of knowledge representation, have been widely applied in the real world. Recently, few-shot knowledge graph completion (FKGC), which aims to predict missing facts for unseen relations with few-shot associated facts, has attracted increasing attention from practitioners and researchers. However, existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems. Meanwhile, they are incompetent at estimating uncertainties in predictions, which is critically important as model predictions could be very unreliable in few-shot settings. Furthermore, most of them cannot handle complex relations and ignore path information in KGs, which largely limits their performance. In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC). Specifically, we unify normalizing flows and neural processes to model a complex distribution of KG completion functions. This offers a novel way to predict facts for few-shot relations while estimating the uncertainty. Then, we propose a stochastic ManifoldE decoder to incorporate the neural process and handle complex relations in few-shot settings. To further improve performance, we introduce an attentive relation path-based graph neural network to capture path information in KGs. Extensive experiments on three public datasets demonstrate that our method significantly outperforms the existing FKGC methods and achieves state-of-the-art performance. Code is available at https://github.com/RManLuo/NP-FKGC.git.

Accepted by SIGIR2023

References in corpus (19)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• Variational Inference with Normalizing Flows
• Normalizing Flows: An Introduction and Review of Current Methods
• Complex Embeddings for Simple Link Prediction
• Normalizing Flows for Probabilistic Modeling and Inference
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• GOOD-D: On Unsupervised Graph Out-Of-Distribution Detection
• Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
• Neural Processes
• Sequential Neural Processes
• Ultrahyperbolic Knowledge Graph Embeddings
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation
• Few-shot Relational Reasoning via Connection Subgraph Pretraining
• Message Passing Neural Processes
• Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
• How Neural Processes Improve Graph Link Prediction
• Neural Processes with Stochastic Attention: Paying more attention to the context dataset

Cited by in corpus (4)

• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• Learning Strong Graph Neural Networks with Weak Information
• ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion
• Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users