Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Understand

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.