New Frontiers of Knowledge Graph Reasoning: Recent Advances and Future Trends

Knowledge graph reasoning plays an important role in data mining, AI, Web, and social science. These knowledge graphs serve as intuitive repositories of human knowledge, allowing for the inference of new information. However, traditional symbolic reasoning, while powerful in its own right, faces challenges posed by incomplete and noisy data in the knowledge graphs. In contrast, recent years have witnessed the emergence of Neural Symbolic AI, an exciting development that fuses the capabilities of deep learning and symbolic reasoning. It aims to create AI systems that are not only highly interpretable and explainable but also incredibly versatile, effectively bridging the gap between symbolic and neural approaches. Furthermore, with the advent of large language models, the integration of LLMs with knowledge graph reasoning has emerged as a prominent frontier, offering the potential to unlock unprecedented capabilities. This tutorial aims to comprehensively review different aspects of knowledge graph reasoning applications and also introduce the recent advances about Neural Symbolic reasoning and combining knowledge graph reasoning with large language models. It is intended to benefit researchers and practitioners in the fields of data mining, AI, Web, and social science.