Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning

Autor:	Xu, Xiaoran, Feng, Wei, Jiang, Yunsheng, Xie, Xiaohui, Sun, Zhiqing, Deng, Zhi-Hong
Rok vydání:	2019
Předmět:	Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: ICLR2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1909.11334 Zobrazit plný text záznamu View this record from Arxiv