Journal article
Graph Representation Learning Based on Cognitive Spreading Activations
IEEE transactions on knowledge and data engineering, Vol.36(12), pp.8408-8420
12/2024
DOI: 10.1109/TKDE.2024.3437781
Abstract
Graph representation learning is an emerging area for graph analysis and inference. However, existing approaches for large-scale graphs either sample nodes in sequential walks or manipulate the adjacency matrices of graphs. The former approach can cause sampling bias against less-connected nodes, whereas the latter may suffer from sparsity that exists in many real-world graphs. To learn from structural information in a graph more efficiently and comprehensively, this paper proposes a new graph representation learning approach inspired by the cognitive model of spreading-activation mechanisms in human memory. This approach learns node embeddings by adopting a graph activation model that allows nodes to "activate" their neighbors and spread their own structural information to other nodes through the paths simultaneously. Comprehensive experiments demonstrate that the proposed model performs better than existing methods on several empirical datasets for multiple graph inference tasks. Meanwhile, the spreading-activation-based model is computationally more efficient than existing approaches-the training process converges after only a small number of iterations, and the training time is linear in the number of edges in a graph. The proposed method works for both homogeneous and heterogeneous graphs
Details
- Title: Subtitle
- Graph Representation Learning Based on Cognitive Spreading Activations
- Creators
- Jie Bai - Institute of AutomationKang Zhao - University of IowaLinjing Li - Institute of AutomationDaniel Zeng - Institute of AutomationQiudan Li - Institute of AutomationFan Yang - Institute of AutomationQuannan Zu - Tianjin University
- Resource Type
- Journal article
- Publication Details
- IEEE transactions on knowledge and data engineering, Vol.36(12), pp.8408-8420
- Publisher
- IEEE
- DOI
- 10.1109/TKDE.2024.3437781
- ISSN
- 1041-4347
- eISSN
- 1558-2191
- Grant note
- New Generation Artificial Intelligence Development Plan of China (2015-2030): 2021ZD0111202 National Natural Science Foundation of China: 72293575, 71902179, 72293573, 62071467, 71974187
This work was supported in part by the New Generation Artificial Intelligence Development Plan of China (2015-2030) under Grant 2021ZD0111202, in part by the National Natural Science Foundation of China under Grant 72293575, Grant 71902179, Grant 72293573, Grant 62071467, and Grant 71974187.
- Language
- English
- Electronic publication date
- 08/01/2024
- Date published
- 12/2024
- Academic Unit
- Business Analytics
- Record Identifier
- 9984696672502771
Metrics
1 Record Views