Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
This work addresses scalability and interpretability issues in knowledge graph reasoning for AI applications, representing an incremental improvement with a novel hybrid method.
The authors tackled the problem of large-scale knowledge graph reasoning by proposing Dynamically Pruned Message Passing Networks (DPMPN), which learn input-dependent subgraphs to model reasoning processes, resulting in clear graphical explanations and accurate predictions that outperform most state-of-the-art methods.
We propose Dynamically Pruned Message Passing Networks (DPMPN) for large-scale knowledge graph reasoning. In contrast to existing models, embedding-based or path-based, we learn an input-dependent subgraph to explicitly model reasoning process. Subgraphs are dynamically constructed and expanded by applying graphical attention mechanism conditioned on input queries. In this way, we not only construct graph-structured explanations but also enable message passing designed in Graph Neural Networks (GNNs) to scale with graph sizes. We take the inspiration from the consciousness prior proposed by and develop a two-GNN framework to simultaneously encode input-agnostic full graph representation and learn input-dependent local one coordinated by an attention module. Experiments demonstrate the reasoning capability of our model that is to provide clear graphical explanations as well as deliver accurate predictions, outperforming most state-of-the-art methods in knowledge base completion tasks.