Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

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