Date(s) - 30/06/2023
11 h 00 - 12 h 00
CNAM, accès 35, salle 35.1.53
Speaker: Lazhar Labiod (Université Paris Cité)
Title: Attributed Graph embedding and clustering
Abstract:Representation learning is a central problem of Attributed Networks data analysis in a variety of fields. Given an attributed graph, the objectives are to obtain a representation of nodes and a partition of the set of nodes. Usually these two objectives are pursued separately via two tasks that are performed sequentially, and any benefit that may be obtained by performing them simultaneously is lost. In this talk we present some simultaneous approaches combining both tasks, embedding and clustering. To jointly encode data affinity between node links and attributes, we use a new powered proximity matrix. We formulate new matrix decomposition models to obtain node representation and node clustering simultaneously. Theoretical analysis indicates the strong links between the newly constructed proximity matrix and both the random walk theory on a graph and a simple Graph Convolutional Network (GCN). Experimental results demonstrate that the proposed algorithms perform better, in terms of clustering and embedding, than state-of-the-art algorithms including deep learning methods designed for similar tasks in relation to attributed network datasets with different characteristics.
Informations pratiques : On pourra participer au séminaire à distance en cliquant sur ce lien Teams (Code secret : rApuAu)