Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Xi Victoria Lin, Richard Socher, Caiming Xiong


Abstract
Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the correct answer. We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.
Anthology ID:
D18-1362
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Editors:
Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3243–3253
Language:
URL:
https://aclanthology.org/D18-1362
DOI:
10.18653/v1/D18-1362
Bibkey:
Cite (ACL):
Xi Victoria Lin, Richard Socher, and Caiming Xiong. 2018. Multi-Hop Knowledge Graph Reasoning with Reward Shaping. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3243–3253, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Multi-Hop Knowledge Graph Reasoning with Reward Shaping (Lin et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1362.pdf
Attachment:
 D18-1362.Attachment.pdf
Video:
 https://aclanthology.org/D18-1362.mp4
Code
 salesforce/MultiHopKG +  additional community code
Data
NELL-995