Skip to Main content Skip to Navigation
Conference papers

Kernel Node Embeddings

Abdulkadir Çelikkanat 1, 2, 3 Fragkiskos Malliaros 1, 2, 3 
2 OPIS - OPtimisation Imagerie et Santé
Inria Saclay - Ile de France, CVN - Centre de vision numérique
Abstract : Learning representations of nodes in a low dimensional space is a crucial task with many interesting applications in network analysis, including link prediction and node classification. Two popular approaches for this problem include matrix factorization and random walk-based models. In this paper, we aim to bring together the best of both worlds, towards learning latent node representations. In particular, we propose a weighted matrix factorization model which encodes random walk-based information about the nodes of the graph. The main benefit of this formulation is that it allows to utilize kernel functions on the computation of the embeddings. We perform an empirical evaluation on real-world networks, showing that the proposed model outperforms baseline node embedding algorithms in two downstream machine learning tasks.
Complete list of metadata

Cited literature [33 references]  Display  Hide  Download
Contributor : Fragkiskos Malliaros Connect in order to contact the contributor
Submitted on : Tuesday, December 24, 2019 - 6:40:46 PM
Last modification on : Saturday, June 25, 2022 - 8:30:12 PM
Long-term archiving on: : Wednesday, March 25, 2020 - 3:08:06 PM


Files produced by the author(s)


  • HAL Id : hal-02423629, version 1


Abdulkadir Çelikkanat, Fragkiskos Malliaros. Kernel Node Embeddings. GlobalSIP 2019 - 7th IEEE Global Conference on Signal and Information Processing, Nov 2019, Ottawa, Canada. ⟨hal-02423629⟩



Record views


Files downloads