Incomplete Graph Learning: A Comprehensive Survey
Riting Xia, Huibo Liu, Anchen Li, Xueyan Liu, Yan Zhang, Chunxu Zhang, Bo Yang
TL;DR
This survey organizes incomplete graph learning around three main incompleteness types (attribute-incomplete, attribute-missing, and hybrid-absent) and provides a comprehensive taxonomy of graphs, incomplete graphs, and learning techniques. It contrasts traditional matrix completion with graph-based imputation, highlights a spectrum of GNN-based approaches, and examines label-prediction and graph-representation learning within incomplete graphs. The review covers attribute-incomplete, attribute-missing, and hybrid-absent methods, detailing data-imputation and label-prediction strategies, encoder–decoder GAEs, and attention-based heterogeneous graph models, while also surveying datasets, processing modes, evaluation metrics, and applications in knowledge graphs, transportation, and recommendations. Looking forward, the authors discuss interpretability, robustness, learning on more complex graph types, multi-pretext-task paradigms, broader domains, and potential integration with large language models to advance practical impact. An online resource accompanies the survey to track ongoing research and developments in incomplete graph learning.
Abstract
Graph learning is a prevalent field that operates on ubiquitous graph data. Effective graph learning methods can extract valuable information from graphs. However, these methods are non-robust and affected by missing attributes in graphs, resulting in sub-optimal outcomes. This has led to the emergence of incomplete graph learning, which aims to process and learn from incomplete graphs to achieve more accurate and representative results. In this paper, we conducted a comprehensive review of the literature on incomplete graph learning. Initially, we categorize incomplete graphs and provide precise definitions of relevant concepts, terminologies, and techniques, thereby establishing a solid understanding for readers. Subsequently, we classify incomplete graph learning methods according to the types of incompleteness: (1) attribute-incomplete graph learning methods, (2) attribute-missing graph learning methods, and (3) hybrid-absent graph learning methods. By systematically classifying and summarizing incomplete graph learning methods, we highlight the commonalities and differences among existing approaches, aiding readers in selecting methods and laying the groundwork for further advancements. In addition, we summarize the datasets, incomplete processing modes, evaluation metrics, and application domains used by the current methods. Lastly, we discuss the current challenges and propose future directions for incomplete graph learning, with the aim of stimulating further innovations in this crucial field. To our knowledge, this is the first review dedicated to incomplete graph learning, aiming to offer valuable insights for researchers in related fields.We developed an online resource to follow relevant research based on this review, available at https://github.com/cherry-a11y/Incomplete-graph-learning.git