Alignment and stability of embeddings: measurement and inference improvement

Autor: Gürsoy, Furkan, Haddad, Mounir, Bothorel, Cécile

Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the same informat

Externí odkaz: http://arxiv.org/abs/2101.07251

Temporalizing static graph autoencoders to handle temporal networks

Autor: Haddad, Mounir, Bothorel, Cécile, Lenca, Philippe, Bedart, Dominique

Publikováno v: 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), Nov 2021, The Hague, Netherlands

International audience; Graph autoencoders (GAE), also known as graph embedding methods, learn latent representations of the nodes of a graph in a low-dimensional space where the structural information is preserved. While real-world graphs are genera

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fb44965e56a986be4e68a0513a0f3cd
https://doi.org/10.1145/3487351.3488333