Logic Diffusion for Knowledge Graph Reasoning
This addresses a generalization bottleneck in knowledge graph reasoning, which is incremental but important for applications like question answering and recommendation systems.
The paper tackles the problem of weak generalization to unseen logical queries in knowledge graph reasoning by proposing a plug-in module called Logic Diffusion (LoD), which improves state-of-the-art models on four public datasets.
Most recent works focus on answering first order logical queries to explore the knowledge graph reasoning via multi-hop logic predictions. However, existing reasoning models are limited by the circumscribed logical paradigms of training samples, which leads to a weak generalization of unseen logic. To address these issues, we propose a plug-in module called Logic Diffusion (LoD) to discover unseen queries from surroundings and achieves dynamical equilibrium between different kinds of patterns. The basic idea of LoD is relation diffusion and sampling sub-logic by random walking as well as a special training mechanism called gradient adaption. Besides, LoD is accompanied by a novel loss function to further achieve the robust logical diffusion when facing noisy data in training or testing sets. Extensive experiments on four public datasets demonstrate the superiority of mainstream knowledge graph reasoning models with LoD over state-of-the-art. Moreover, our ablation study proves the general effectiveness of LoD on the noise-rich knowledge graph.