Idioma:

Don't Walk, Skip: Online Learning of Multi-scale Network Embeddings

Perozzi, Bryan ; Kulkarni, Vivek ; Chen, Haochen ; Skiena, Steven Xu, Guandong ; Ferrari, Elena ; Diesner, Jana

Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, 2017, p.258-265

New York, NY, USA: ACM

Texto completo disponível

Citações Citado por

Enviar para

Título:
Don't Walk, Skip: Online Learning of Multi-scale Network Embeddings
Autor: Perozzi, Bryan ; Kulkarni, Vivek ; Chen, Haochen ; Skiena, Steven
Xu, Guandong ; Ferrari, Elena ; Diesner, Jana
Assuntos: Human-centered computing ; Human-centered computing -- Human computer interaction (HCI) ; Human-centered computing -- Human computer interaction (HCI) -- Interaction paradigms ; Human-centered computing -- Human computer interaction (HCI) -- Interaction paradigms -- Web-based interaction ; Information systems ; Information systems -- Information systems applications ; Information systems -- Information systems applications -- Data mining
É parte de: Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2017, 2017, p.258-265
Descrição: We present WALKLETS, a novel approach for learning multiscale representations of vertices in a network. In contrast to previous works, these representations explicitly encode multi-scale vertex relationships in a way that is analytically derivable. WALKLETS generates these multiscale relationships by sub-sampling short random walks on the vertices of a graph. By 'skipping' over steps in each random walk, our method generates a corpus of vertex pairs which are reachable via paths of a fixed length. This corpus can then be used to learn a series of latent representations, each of which captures successively higher order relationships from the adjacency matrix. We demonstrate the efficacy of WALKLETS's latent representations on several multi-label network classification tasks for social networks such as BlogCatalog, DBLP, Flickr, and YouTube. Our results show that WALKLETS outperforms new methods based on neural matrix factorization. Specifically, we outperform DeepWalk by up to 10% and LINE by 58% Micro-F1 on challenging multi-label classification tasks. Finally, WALKLETS is an online algorithm, and can easily scale to graphs with millions of vertices and edges.
Editor: New York, NY, USA: ACM
Idioma: Inglês

Voltar para lista de resultados

Anterior Resultado 7 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

Don't Walk, Skip: Online Learning of Multi-scale Network Embeddings

Perozzi, Bryan ; Kulkarni, Vivek ; Chen, Haochen ; Skiena, Steven Xu, Guandong ; Ferrari, Elena ; Diesner, Jana

New York, NY, USA: ACM

Buscando em bases de dados remotas. Favor aguardar.