用图神经网络解决不完整知识图谱的任意连接查询问题
One Model, Any Conjunctive Query: Graph Neural Networks for Answering Queries over Incomplete Knowledge Graphs
- 基于强化学习训练图神经网络，统一处理各类连接查询
- 仅在小规模数据上训练，即可准确判断和检索大规模复杂查询答案
- 可迁移至新知识图谱，适合处理缺失数据场景
针对现代知识图谱的不完整性，一种新的问答范式应运而生：预测那些不在原图中但存在于图补全中的答案。本文正式提出并研究了两类问答问题：答案分类与答案检索。为此，我们提出AnyCQ模型，可对任意知识图谱上的任意连接查询进行答案分类。该框架核心是一个通过强化学习目标训练的图神经网络，用于回答布尔型查询。模型仅在简单、小规模实例上训练，即可泛化到任意结构的大规模查询，可靠地分类和检索现有方法无法处理的查询答案。这通过我们新提出的挑战性基准进行了实证验证。最后，我们实证表明，当配备合适的链接预测模型时，AnyCQ能有效迁移到完全新的知识图谱，展现出其在不完整数据查询中的潜力。
原文摘要 · Abstract (English)
Motivated by the incompleteness of modern knowledge graphs, a new setup for query answering has emerged, where the goal is to predict answers that do not necessarily appear in the knowledge graph, but are present in its completion. In this paper, we formally introduce and study two query answering problems, namely, query answer classification and query answer retrieval. To solve these problems, we propose AnyCQ, a model that can classify answers to any conjunctive query on any knowledge graph. At the core of our framework lies a graph neural network trained using a reinforcement learning objective to answer Boolean queries. Trained only on simple, small instances, AnyCQ generalizes to large queries of arbitrary structure, reliably classifying and retrieving answers to queries that existing approaches fail to handle. This is empirically validated through our newly proposed, challenging benchmarks. Finally, we empirically show that AnyCQ can effectively transfer to completely novel knowledge graphs when equipped with an appropriate link prediction model, highlighting its potential for querying incomplete data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。