Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding

Abstract

Knowledge graph (KG) embedding is well-known in learning representations of KGs. Many models have been proposed to learn the interactions between entities and relations of the triplets. However, long-term information among multiple triplets is also important to KG. In this work, based on the relational paths, which are composed of a sequence of triplets, we define the Interstellar as a recurrent neural architecture search problem for the short-term and long-term information along the paths. First, we analyze the difficulty of using a unified model to work as the Interstellar. Then, we propose to search for recurrent architecture as the Interstellar for different KG tasks. A case study on synthetic data illustrates the importance of the defined search problem. Experiments on real datasets demonstrate the effectiveness of the searched models and the efficiency of the proposed hybrid-search algorithm.

Accepted to NeurIPS 2020

References in corpus (12)

• Neural Architecture Search with Reinforcement Learning
• Neural Architecture Search: A Survey
• DARTS: Differentiable Architecture Search
• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• Designing Neural Network Architectures using Reinforcement Learning
• Gated Feedback Recurrent Neural Networks
• Understanding and Robustifying Differentiable Architecture Search
• The Evolved Transformer
• Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs
• Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
• DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
• Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

Cited by in corpus (3)

• Knowledge Graph Reasoning with Relational Digraph
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap