Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective
Lihui Liu, Zihao Wang, Hanghang Tong
TL;DR
This survey addresses the problem of reasoning over knowledge graphs in the presence of incomplete and noisy data by combining neural and symbolic approaches. It catalogs single-hop, complex logic, natural language query answering, and the integration of large language models with knowledge graph reasoning, detailing symbolic methods, neural embeddings, neural-symbolic hybrids, and reinforcement learning strategies. It highlights how neural-symbolic methods blend the interpretability of symbolic reasoning with the robustness of neural models, and discusses LLM based collaboration to augment KG reasoning and mitigate incompleteness. The paper concludes with future directions including multi-modal knowledge graphs and cross-lingual reasoning to broaden applicability and impact.
Abstract
Knowledge graph reasoning is pivotal in various domains such as data mining, artificial intelligence, the Web, and social sciences. These knowledge graphs function as comprehensive repositories of human knowledge, facilitating the inference of new information. Traditional symbolic reasoning, despite its strengths, struggles with the challenges posed by incomplete and noisy data within these graphs. In contrast, the rise of Neural Symbolic AI marks a significant advancement, merging the robustness of deep learning with the precision of symbolic reasoning. This integration aims to develop AI systems that are not only highly interpretable and explainable but also versatile, effectively bridging the gap between symbolic and neural methodologies. Additionally, the advent of large language models (LLMs) has opened new frontiers in knowledge graph reasoning, enabling the extraction and synthesis of knowledge in unprecedented ways. This survey offers a thorough review of knowledge graph reasoning, focusing on various query types and the classification of neural symbolic reasoning. Furthermore, it explores the innovative integration of knowledge graph reasoning with large language models, highlighting the potential for groundbreaking advancements. This comprehensive overview is designed to support researchers and practitioners across multiple fields, including data mining, AI, the Web, and social sciences, by providing a detailed understanding of the current landscape and future directions in knowledge graph reasoning.