1 code implementation • 29 Aug 2023 • Nikolaos Nakis, Abdulkadir Çelikkanat, Morten Mørup
Graph representation learning (GRL) has become a prominent tool for furthering the understanding of complex networks providing tools for network embedding, link prediction, and node classification.
1 code implementation • 23 Jan 2023 • Nikolaos Nakis, Abdulkadir Çelikkanat, Louis Boucherie, Christian Djurhuus, Felix Burmester, Daniel Mathias Holmelund, Monika Frolcová, Morten Mørup
On four real social signed networks of polarization, we demonstrate that the model extracts low-dimensional characterizations that well predict friendships and animosity while providing interpretable visualizations defined by extreme positions when endowing the model with an embedding space restricted to polytopes.
no code implementations • 23 Dec 2022 • Abdulkadir Çelikkanat, Nikolaos Nakis, Morten Mørup
We further impose a scalable Kronecker structured Gaussian Process prior to the dynamics accounting for community structure, temporal smoothness, and disentangled (uncorrelated) latent embedding dimensions optimally learned to characterize the network dynamics.
1 code implementation • 12 Apr 2022 • Nikolaos Nakis, Abdulkadir Çelikkanat, Sune Lehmann Jørgensen, Morten Mørup
This paper proposes a novel scalable graph representation learning method named the Hierarchical Block Distance Model (HBDM).
no code implementations • 10 Nov 2021 • Abdulkadir Çelikkanat, Fragkiskos D. Malliaros
Network representation learning (NRL) methods have received significant attention over the last years thanks to their success in several graph analysis problems, including node classification, link prediction, and clustering.
no code implementations • 1 Oct 2020 • Abdulkadir Çelikkanat, Fragkiskos D. Malliaros, Apostolos N. Papadopoulos
Graph Representation Learning (GRL) has become a key paradigm in network analysis, with a plethora of interdisciplinary applications.
no code implementations • 20 Nov 2019 • Abdulkadir Çelikkanat, Fragkiskos D. Malliaros
We introduce the generic \textit{exponential family graph embedding} model, that generalizes random walk-based network representation learning techniques to exponential family conditional distributions.
1 code implementation • 8 Sep 2019 • Abdulkadir Çelikkanat, Fragkiskos D. Malliaros
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.
no code implementations • 16 Oct 2018 • Abdulkadir Çelikkanat, Fragkiskos D. Malliaros
Although various approaches have been proposed to compute node embeddings, many successful methods benefit from random walks in order to transform a given network into a collection of sequences of nodes and then they target to learn the representation of nodes by predicting the context of each vertex within the sequence.