Learning Graph Representations With Maximal Cliques.
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Publication Type:
- Journal Article
- IEEE Trans Neural Netw Learn Syst, 2021, PP, (99)
- Issue Date:
|Learning_Graph_Representations_With_Maximal_Cliques.pdf||Published version||2.07 MB|
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Non-Euclidean property of graph structures has faced interesting challenges when deep learning methods are applied. Graph convolutional networks (GCNs) can be regarded as one of the successful approaches to classification tasks on graph data, although the structure of this approach limits its performance. In this work, a novel representation learning approach is introduced based on spectral convolutions on graph-structured data in a semisupervised learning setting. Our proposed method, COnvOlving cLiques (COOL), is constructed as a neighborhood aggregation approach for learning node representations using established GCN architectures. This approach relies on aggregating local information by finding maximal cliques. Unlike the existing graph neural networks which follow a traditional neighborhood averaging scheme, COOL allows for aggregation of densely connected neighboring nodes of potentially differing locality. This leads to substantial improvements on multiple transductive node classification tasks.
Please use this identifier to cite or link to this item: