Multiscale Representation Learning of Graph Data With Node Affinity

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Multiscale Representation Learning of Graph Data With Node Affinity

By: 
Xing Gao; Wenrui Dai; Chenglin Li; Hongkai Xiong; Pascal Frossard

Graph neural networks have emerged as a popular and powerful tool for learning hierarchical representation of graph data. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of data in graph neural networks. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node affinity to improve the hierarchical representation learning of graph data. Node affinity is computed by harmonizing the kernel representation of topology information and node features. In particular, a structure-aware kernel representation is introduced to explicitly exploit advanced topological information for efficient graph pooling without eigendecomposition of the graph Laplacian. Similarities of node signals are evaluated using the Gaussian radial basis function (RBF) in an adaptive way. Experimental results demonstrate that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.

SPS on Twitter

  • Students, it's time to form your teams! The 2022 Signal Processing Cup competition is underway. This year's topic,… https://t.co/fVw7tA7zTG
  • The DEGAS Webinar Series continues this Thursday, 13 January when Peter Battaglia presents "Modeling Physical Struc… https://t.co/Kndvzl8BpE
  • The SPS Webinar Series continues on Wednesday, 26 January when Dr. Ba-Ngu Vo presents "Bayesian Multi-object Tracki… https://t.co/sKejcUeyys
  • Call for Speakers! The IEEE Women in Engineering International Leadership Conference () is seeking submissio… https://t.co/bSaRgMw2uD
  • CALL FOR PROPOSALS: The SPS Education Board is soliciting proposals for short courses in conjunction with ICASSP 20… https://t.co/LiVjYgEVGU

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar