Efficient Graph Convolution for Joint Node Representation Learning and Clustering - Archive ouverte HAL
Communication Dans Un Congrès Année : 2022

Efficient Graph Convolution for Joint Node Representation Learning and Clustering

Chakib Fettal
Lazhar Labiod
Mohamed Nadif

Résumé

Attributed graphs are used to model a wide variety of real-world networks. Recent graph convolutional network-based representation learning methods have set state-of-the-art results on the clustering of attributed graphs. However, these approaches deal with clustering as a downstream task while better performances can be attained by incorporating the clustering objective into the representation learning process. In this paper, we propose, in a unified framework, an objective function taking into account both tasks simultaneously. Based on a variant of the simple graph convolutional network, our model does clustering by minimizing the difference between the convolved node representations and their reconstructed cluster representatives. We showcase the efficiency of the derived algorithm against state-of-the-art methods both in terms of clustering performance and computational cost on thede facto benchmark graph clustering datasets. We further demonstrate the usefulness of the proposed approach for graph visualization through generating embeddings that exhibit a clustering structure.
Fichier non déposé

Dates et versions

hal-03632417 , version 1 (06-04-2022)

Identifiants

Citer

Chakib Fettal, Lazhar Labiod, Mohamed Nadif. Efficient Graph Convolution for Joint Node Representation Learning and Clustering. WSDM '22: The Fifteenth ACM International Conference on Web Search and Data Mining, Feb 2022, Virtual Event AZ USA, United States. pp.289-297, ⟨10.1145/3488560.3498533⟩. ⟨hal-03632417⟩
210 Consultations
0 Téléchargements

Altmetric

Partager

More