Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

Abstract

We study the problem of knowledge graph (KG) embedding. A widely-established assumption to this problem is that similar entities are likely to have similar relational roles. However, existing related methods derive KG embeddings mainly based on triple-level learning, which lack the capability of capturing long-term relational dependencies of entities. Moreover, triple-level learning is insufficient for the propagation of semantic information among entities, especially for the case of cross-KG embedding. In this paper, we propose recurrent skipping networks (RSNs), which employ a skipping mechanism to bridge the gaps between entities. RSNs integrate recurrent neural networks (RNNs) with residual learning to efficiently capture the long-term relational dependencies within and between KGs. We design an end-to-end framework to support RSNs on different tasks. Our experimental results showed that RSNs outperformed state-of-the-art embedding-based methods for entity alignment and achieved competitive performance for KG completion.

Accepted by the 36th International Conference on Machine Learning (ICML 2019)

Cited by in corpus (26)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs
• Relation Embedding with Dihedral Group in Knowledge Graph
• Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
• Neighborhood Matching Network for Entity Alignment
• On the Ambiguity of Rank-Based Evaluation of Entity Alignment or Link Prediction Methods
• Cross-lingual Entity Alignment with Adversarial Kernel Embedding and Adversarial Knowledge Translation
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• A Self-supervised Method for Entity Alignment
• Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness
• Degree-Aware Alignment for Entities in Tail
• Temporal Knowledge Graph Reasoning Triggered by Memories
• OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• Cross-lingual Entity Alignment with Incidental Supervision
• Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs
• Towards Entity Alignment in the Open World: An Unsupervised Approach
• Reinforcement Learning based Collective Entity Alignment with Adaptive Features
• Knowing the No-match: Entity Alignment with Dangling Cases
• Collective Entity Alignment via Adaptive Features
• Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs
• TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting
• From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment
• HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction