SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning
This addresses the issue of inefficient and unreliable reasoning in knowledge graphs, particularly in sparse settings, for applications like link prediction, but it is incremental as it builds on existing sequence-to-sequence and Transformer methods.
The authors tackled the problem of slow convergence and failure in multi-hop knowledge graph reasoning due to missing edges by introducing SQUIRE, a sequence-to-sequence framework using Transformer, which achieved significant improvement over prior methods and converged 4x-7x faster.
Multi-hop knowledge graph (KG) reasoning has been widely studied in recent years to provide interpretable predictions on missing links with evidential paths. Most previous works use reinforcement learning (RL) based methods that learn to navigate the path towards the target entity. However, these methods suffer from slow and poor convergence, and they may fail to infer a certain path when there is a missing edge along the path. Here we present SQUIRE, the first Sequence-to-sequence based multi-hop reasoning framework, which utilizes an encoder-decoder Transformer structure to translate the query to a path. Our framework brings about two benefits: (1) It can learn and predict in an end-to-end fashion, which gives better and faster convergence; (2) Our Transformer model does not rely on existing edges to generate the path, and has the flexibility to complete missing edges along the path, especially in sparse KGs. Experiments on standard and sparse KGs show that our approach yields significant improvement over prior methods, while converging 4x-7x faster.