no code implementations • sdp (COLING) 2022 • Raef Kazi, Alessandra Amato, ShengHui Wang, Doina Bucur
We develop three visualisation methods that can show, given a root word: the temporal change in its linguistic context, word re-occurrence, degree of similarity, time continuity, and separate trends per publisher location.
1 code implementation • 31 Mar 2024 • Lourens Touwen, Doina Bucur, Remco van der Hofstad, Alessandro Garavaglia, Nelly Litvak
We propose a novel model-selection method for dynamic real-life networks.
Ranked #1 on Graph Classification on Synthetic Dynamic Networks
1 code implementation • 26 May 2023 • Elia Cunegatti, Matteo Farina, Doina Bucur, Giovanni Iacca
With these novelties, we show the following: (a) The proposed MGE allows to extract topological metrics that are much better predictors of the accuracy drop than metrics computed from current input-agnostic BGEs; (b) Which metrics are important at different sparsity levels and for different architectures; (c) A mixture of our topological metrics can rank PaI algorithms more effectively than Ramanujan-based metrics.
1 code implementation • 13 Apr 2022 • Elia Cunegatti, Giovanni Iacca, Doina Bucur
Finding the most influential nodes in a network is a computationally hard problem with several possible applications in various kinds of network-based problems.
no code implementations • 13 Mar 2022 • Bart Verkuil, Carlos E. Budde, Doina Bucur
We obtain fault trees for the 11 failure variables, and evaluate them in two ways: quantitatively, with a significance score, and qualitatively, with domain specialists.
1 code implementation • 16 Feb 2022 • Frank Stapel, Floris Weers, Doina Bucur
We measure the color shifts present in colorized images from the ADE20K dataset, when colorized by the automatic GAN-based DeOldify model.
1 code implementation • 9 Nov 2021 • Thi Kim Nhung Dang, Doina Bucur, Berk Atıl, Guillaume Pitel, Frank Ruis, Hamidreza Kadkhodaei, Nelly Litvak
In the literature, many feature designs have been proposed for predicting changes in the Web.
1 code implementation • 19 Oct 2021 • Doina Bucur
We then form the network of constellations (as linked by their similarity), to study how similar cultures are by computing their assortativity (or homophily) over the network.
1 code implementation • NeurIPS 2021 • Frank Ruis, Gertjan Burghouts, Doina Bucur
Next we propagate the independent prototypes through a compositional graph, to learn compositional prototypes of novel attribute-object combinations that reflect the dependencies of the target distribution.
no code implementations • 13 Jun 2020 • Doina Bucur
Information flow, opinion, and epidemics spread over structured networks.
1 code implementation • Machine Learning and Knowledge Extraction 2019 • Meike Nauta, Doina Bucur, Christin Seifert
We therefore present the Temporal Causal Discovery Framework (TCDF), a deep learning framework that learns a causal graph structure by discovering causal relationships in observational time series data.