I am excited to announce that I have defended my Ph.D. thesis on Advancements in Knowledge Graph Reasoning: Innovative Approaches to Complex Query Answering and Logical Hypothesis Generation on March 7, 2025.
Abstract:
Complex logical query answering on knowledge graphs (KGs) has emerged as a crucial component of knowledge graph reasoning. This thesis presents a comprehensive framework for advancing KG reasoning through multiple novel approaches across diverse knowledge graph types. We introduce Query2Particles (Q2P), a particle-based embedding method that effectively handles distributed answer sets in incomplete KGs by encoding queries into multiple particle embeddings. To address numerical reasoning, we develop the Number Reasoning Network (NRN), which integrates numerical attribute processing with traditional entity-relation reasoning. We further propose Sequential Query Encoding (SQE), transforming computational graphs into sequences for more efficient and accurate query processing. Our work extends to eventuality knowledge graphs through Complex Eventuality Query Answering (CEQA), incorporating implicit temporal and logical constraints via Memory-Enhanced Query Encoding (MEQE). For practical applications, we develop the Logical Session Graph Transformer (LSGT) to understand cross-session user intentions in recommendation systems. Additionally, we advance abductive reasoning through our Reinforcement Learning from Knowledge Graph (RLF-KG) approach, enabling robust logical hypothesis generation. Extensive experiments on benchmark datasets demonstrate that our methods consistently achieve state-of-the-art performance across various tasks, from basic query answering to complex reasoning scenarios. These contributions collectively advance the field of knowledge graph reasoning, providing powerful tools for complex query answering in real-world applications.
The Ph.D. thesis is a culmination of my research journey at the Hong Kong University of Science and Technology under the guidance of Professor Yangqiu Song. I would like to express my deepest gratitude to my advisor, committee members, collaborators, and friends for their support and guidance throughout this journey. I am also thankful to the research community for their valuable feedback and insights that have shaped my research. I look forward to continuing my research journey and contributing to the field of knowledge graph reasoning and natural language understanding.
In the future, I will be working on building Agentic Neural Graph Databases (Agentic-NGDB) to enable more efficient and effective knowledge intensive AI. Stay tuned for more updates on my research journey!