Decentralized Knowledge Graph Representation Learning

Lingbing Guo, Weiqing Wang, Zequn Sun, Chenghao Liu, Wei Hu

Keywords: Representation Learning, Knowledge Graph, Entity Alignment, Knowledge Graph Completion, Knowledge Graph Embedding

Abstract: Knowledge graph (KG) representation learning methods have achieved competitive performance in many KG-oriented tasks, among which the best ones are usually based on graph neural networks (GNNs), a powerful family of networks that learns the representation of an entity by aggregating the features of its neighbors and itself. However, many KG representation learning scenarios only provide the structure information that describes the relationships among entities, causing that entities have no input features. In this case, existing aggregation mechanisms are incapable of inducing embeddings of unseen entities as these entities have no pre-defined features for aggregation. In this paper, we present a decentralized KG representation learning approach, decentRL, which encodes each entity from and only from the embeddings of its neighbors. For optimization, we design an algorithm to distill knowledge from the model itself such that the output embeddings can continuously gain knowledge from the corresponding original embeddings. Extensive experiments show that the proposed approach performed better than many cutting-edge models on the entity alignment task, and achieved competitive performance on the entity prediction task. Furthermore, under the inductive setting, it significantly outperformed all baselines on both tasks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: An inductive KG representation learning approach that only levearges structure information.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=wnATESJxvy