One Model, Any Conjunctive Query: Graph Neural Networks for Answering Complex Queries over Knowledge Graphs

2024-09-21

arXiv.org

AI Summary

Existing knowledge graph completion methods struggle with incompleteness in answering complex conjunctive queries. Method: This paper proposes the first unified single-model framework capable of handling arbitrary-structure conjunctive queries, jointly supporting answer classification and retrieval. It integrates graph neural networks, query embedding, and link prediction, and introduces a novel reinforcement learning–based training paradigm for Boolean queries, along with an answer existence detection mechanism. Contributions/Results: (1) The model achieves strong zero-shot generalization to unseen query structures—first such result for a single model; (2) it enables cross-knowledge-graph zero-shot transfer; and (3) it substantially outperforms state-of-the-art methods on a newly constructed benchmark, demonstrating both high accuracy and robustness.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Traditional query answering over knowledge graphs -- or broadly over relational data -- is one of the most fundamental problems in data management. 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 work, we propose AnyCQ, a graph neural network model that can classify answers to any conjunctive query on any knowledge graph, following training. At the core of our framework lies a graph neural network model trained using a reinforcement learning objective to answer Boolean queries. Our approach and problem setup differ from existing query answering studies in multiple dimensions. First, we focus on the problem of query answer classification: given a query and a set of possible answers, classify these proposals as true or false relative to the complete knowledge graph. Second, we study the problem of query answer retrieval: given a query, retrieve an answer to the query relative to the complete knowledge graph or decide that no correct solutions exist. Trained on simple, small instances, AnyCQ can generalize to large queries of arbitrary structure, reliably classifying and retrieving answers to samples where existing approaches fail, which is empirically validated on new and challenging benchmarks. Furthermore, we demonstrate that our AnyCQ models effectively transfer to out-of-distribution knowledge graphs, when equipped with a relevant link predictor, highlighting their potential to serve as a general engine for query answering.

Problem

• Predict answers missing in incomplete knowledge graphs
• Classify and retrieve answers to any conjunctive query
• Generalize to large queries with arbitrary structures

Innovation

• Graph Neural Network for query answering
• Reinforcement learning for Boolean queries
• Transfer learning to novel knowledge graphs