Graph Learning: A Survey

By Feng Xia, Ke Sun, Shuo Yu, Abdul Aziz, Liangtian Wan, Shirui Pan, Huan Liu. IEEE Transactions on Artificial Intelligence, 2021

510 citations recorded by the source corpus.

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/57fbaf35321b2c4c4c0cc2b63e72bfb9c5d5d9c9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jiliang Tang
2. Dawei Yin
3. Hui Liu
4. Wenqi Fan
5. Yue Liu
6. Siwei Wang
7. Lingyuan Meng
8. Wenxuan Tu

In Computer Vision and Pattern Recognition

1. Jiliang Tang
2. Yue Liu
3. Siwei Wang
4. Wenxuan Tu
5. Ran Wang
6. Farhad Pourpanah
7. Xinwang Liu
8. Yuxuan Luo

In Statistical and Nonlinear Physics

1. Wei Jin
2. Jiliang Tang
3. Xinwang Liu
4. Feng Xia
5. Hang Li

Citations in the corpus

• Exploring the Potential of Large Language Models (LLMs)in Learning on Graphs (2023, background): “Graphs are ubiquitous in various disciplines and applications, encompassing a wide range of real-world scenarios [73].”
• Knowledge Graphs: Opportunities and Challenges (2023, background): “The aim of knowledge graph embeddings is to effectively represent knowledge graphs in a low-dimensional vector space while still preserving the semantics (Xia et al. 2021; Vashishth et al. 2020).”
• A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal (2022, background): “Nowadays, more and more KGR models are developed based on neural networks, such as GNN [304].”
• A Review of Generalized Zero-Shot Learning Methods (2020, background): “Machine learning techniques convert graphbased properties into a set of features without projecting the extracted information into a lower dimensional space [98].”
• RAG vs. GraphRAG: A Systematic Evaluation and Key Insights (2025, unknown): “To ensure fair comparison, we evaluate RAG and GraphRAG under identical settings whenever applicable, and otherwise follow the default configurations of each method while matching key budgets.”