Neural Architectures for Searching Subgraph Structures

With the development of new neural network architectures for graph representation learning in recent years, the use of graphs to store, represent and process data has become increasingly more important. This thesis focuses on both structural and semantic aspects of graphs in order to design and develop neural representation learning models that are capable of performing effective and efficient search on graphs in order to identify and retrieve relevant subgraph structures. Graph search is an NP-hard problem, with existing methods struggling to balance accuracy and efficiency. This work aims to design robust neural representations that address these challenges. The first contribution examines team formation as a case study of search within complete graphs. Team formation is concerned with the identification of a group of experts who have a high likelihood of effectively collaborating with each other in order to satisfy a collection of input skills. This thesis proposes a variational Bayesian neural network architecture that learns representations for teams whose members have collaborated with each other in the past. The learnt representations allow our proposed approach to mine teams that have a past collaborative history and collectively cover the requested desirable set of skills. Through our experiments on DBLP and Dota2 datasets, we demonstrate that our approach shows stronger performance compared to a range of strong team formation techniques from both quantitative and quality perspectives. Furthermore, we redefine team discovery as a task of learning subgraph representations from heterogeneous collaboration networks. Our method captures both local (node interactions within teams) and global (subgraph interactions between teams) characteristics, enabling seamless mapping between homogeneous and heterogeneous subgraphs to effectively discover teams. Extensive experiments on two real-world datasets confirm the effectiveness of the approach. In the context of incomplete graphs, we introduce a novel graph neural network representation learning technique specifically tailored for graphs with missing information. We propose a novel keyword graph representation learning method that incorporates complementary aspects of graphs: global, local, adjusted, and feature semantics. Considering these multiple aspects, our approach remains robust and resilient to missing information. We adopt and fine-tune a transformer-based model to aggregate the various features of a graph to generate rich representations, recognizing the pivotal role of keywords in this task. We show through experiments on real-world data that our method outperforms the state-ofthe-art approaches and is particularly robust in the face of missing values, underscoring its ability to effectively handle incomplete graphs.