Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.03125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911948074909696 |
|---|---|
| author | Huang, Yu Zhou, Min Yang, Menglin Wang, Zhen Zhang, Muhan Wang, Jie Xie, Hong Wang, Hao Lian, Defu Chen, Enhong |
| author_facet | Huang, Yu Zhou, Min Yang, Menglin Wang, Zhen Zhang, Muhan Wang, Jie Xie, Hong Wang, Hao Lian, Defu Chen, Enhong |
| contents | Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Notably, Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. With these models being usually characterized by intuition-driven design or highly intricate components, placing them within the theoretical analysis framework to distill the core concepts, helps understand the key principles that drive the functionality better and guide further development. Given this surge in interest, this article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models. Encompassing discussions on fundamental aspects such as expressiveness power, generalization, optimization, and unique phenomena such as over-smoothing and over-squashing, this piece delves into the theoretical foundations and frontier driving the evolution of graph learning. In addition, this article also presents several challenges and further initiates discussions on possible solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03125 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Foundations and Frontiers of Graph Learning Theory Huang, Yu Zhou, Min Yang, Menglin Wang, Zhen Zhang, Muhan Wang, Jie Xie, Hong Wang, Hao Lian, Defu Chen, Enhong Machine Learning Artificial Intelligence Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Notably, Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. With these models being usually characterized by intuition-driven design or highly intricate components, placing them within the theoretical analysis framework to distill the core concepts, helps understand the key principles that drive the functionality better and guide further development. Given this surge in interest, this article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models. Encompassing discussions on fundamental aspects such as expressiveness power, generalization, optimization, and unique phenomena such as over-smoothing and over-squashing, this piece delves into the theoretical foundations and frontier driving the evolution of graph learning. In addition, this article also presents several challenges and further initiates discussions on possible solutions. |
| title | Foundations and Frontiers of Graph Learning Theory |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.03125 |