SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning

01/17/2022
by   Yushi Bai, et al.
0

Multi-hop knowledge graph (KG) reasoning has been widely studied in recent years to provide interpretable predictions on missing links. Given a triple query, multi-hop reasoning task aims to give an evidential path that indicates the inference process. Most previous works use reinforcement learning (RL) based method that learns 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 structure to translate the query to a path. Our model design brings about two benefits: (1) It can learn and predict in an end-to-end fashion, which gives better and faster convergence; (2) Our 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/05/2020

Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph

Multi-hop reasoning has been widely studied in recent years to seek an e...
research
09/03/2022

MMKGR: Multi-hop Multi-modal Knowledge Graph Reasoning

Multi-modal knowledge graphs (MKGs) include not only the relation triple...
research
10/28/2021

SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs

Knowledge graphs (KGs) capture knowledge in the form of head–relation–ta...
research
12/04/2019

Cooperative Reasoning on Knowledge Graph and Corpus: A Multi-agentReinforcement Learning Approach

Knowledge-graph-based reasoning has drawn a lot of attention due to its ...
research
08/31/2019

Collaborative Policy Learning for Open Knowledge Graph Reasoning

In recent years, there has been a surge of interests in interpretable gr...
research
08/31/2018

Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Multi-hop reasoning is an effective approach for query answering (QA) ov...
research
09/28/2020

Graph-based Multi-hop Reasoning for Long Text Generation

Long text generation is an important but challenging task.The main probl...

Please sign up or login with your details

Forgot password? Click here to reset