Struc2vec: Learning Node Representations from Structural Identity
Author:
Daniel Ratton Figueiredo, Federal University of Rio de Janeiro
Abstract:
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents struc2vec, a novel and flexible framework for learning latent representations for the structural identity of nodes. struc2vec uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while struc2vec exhibits much superior performance in this task, as it overcomes limitations of prior approaches. As a consequence, numerical experiments indicate that struc2vec improves performance on classification tasks that depend more on structural identity.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео Struc2vec: Learning Node Representations from Structural Identity канала KDD2017 video
Daniel Ratton Figueiredo, Federal University of Rio de Janeiro
Abstract:
Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. This work presents struc2vec, a novel and flexible framework for learning latent representations for the structural identity of nodes. struc2vec uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while struc2vec exhibits much superior performance in this task, as it overcomes limitations of prior approaches. As a consequence, numerical experiments indicate that struc2vec improves performance on classification tasks that depend more on structural identity.
More on http://www.kdd.org/kdd2017/
KDD2017 Conference is published on http://videolectures.net/
Видео Struc2vec: Learning Node Representations from Structural Identity канала KDD2017 video
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
struc2vec: Learning Node Representations from Structural IdentityDeep & Cross Network for Ad Click PredictionsIncrementality Bidding & AttributionDeepWalk: Turning Graphs Into Features via Network EmbeddingsCost-sensitive Learning for Utility Optimization in Online Advertising AuctionsLecture 3 Motifs and Structural Roles in NetworksLe Song: "A Framework For Differentiable Discovery Of Graph Algorithms"A/B Testing in Networks with Adversarial MembersLearning over sets, subgraphs, and streams: How to accurately incorporate graph contextAn Ensemble-based Approach to Click-Through Rate Prediction for Promoted Listings at EtsyStacked Ensemble Models and Data Science CompetitionsMachine Learning and Causal Inference for Advertising EffectivenessDmitry Krotov, IBM | Machine Learning WorkshopStanford CS224N: NLP with Deep Learning | Winter 2019 | Lecture 8 – Translation, Seq2Seq, AttentionLearning to Make StuffGraph EmbeddingsLecture 2 | Word Vector Representations: word2vecRafael Gomez-Bombarelli, MIT | Machine Learning WorkshopMentoring Session PanelSELEÇÃO! //🥇09 MELHORES⌚SMARTWATCH & RELÓGIO INTELIGENTES de 2021!