no code implementations • NoDaLiDa 2021 • Abdul Aziz Alkathiri, Lodovico Giaretta, Sarunas Girdzijauskas, Magnus Sahlgren
Advanced NLP models require huge amounts of data from various domains to produce high-quality representations.
1 code implementation • LREC 2022 • Filip Cornell, Chenda Zhang, Jussi Karlgren, Sarunas Girdzijauskas
In this paper, we report experiments on Few- and Zero-shot Knowledge Graph completion, where the objective is to add missing relational links between entities into an existing Knowledge Graph with few or no previous examples of the relation in question.
no code implementations • 25 Jan 2024 • Filip Cornell, Yifei Jin, Jussi Karlgren, Sarunas Girdzijauskas
First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method.
1 code implementation • 20 Apr 2023 • Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas, Aristides Gionis
Cellular coverage quality estimation has been a critical task for self-organized networks.
no code implementations • 8 Jul 2022 • Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas, Aristides Gionis
Accurate routing network status estimation is a key component in Software Defined Networking.
1 code implementation • 17 Jun 2022 • Edvin Listo Zec, Ebba Ekblom, Martin Willbo, Olof Mogren, Sarunas Girdzijauskas
We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks.
1 code implementation • 3 Oct 2021 • Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections.
1 code implementation • 23 Aug 2021 • Zekarias T. Kefato, Sarunas Girdzijauskas, Hannes Stärk
Recently, a number of SSL methods for graph representation learning have achieved performance comparable to SOTA semi-supervised GNNs.
no code implementations • 28 Jul 2021 • Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
We first formulate the user experience prediction problem as a classification task, accounting for the fact that most of the viewers at the beginning of an event have poor quality of experience due to low-bandwidth connections and limited interactions with the tracker.
no code implementations • 19 Apr 2021 • Daniel Garcia Bernal, Lodovico Giaretta, Sarunas Girdzijauskas, Magnus Sahlgren
The results show that neither the quality of the results nor the convergence time in Federated Word2Vec deteriorates as compared to centralised Word2Vec.
2 code implementations • 27 Mar 2021 • Zekarias T. Kefato, Sarunas Girdzijauskas
This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as semi-supervised/supervised techniques.
1 code implementation • 11 Nov 2020 • Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas
We evaluate our proposed model on the link prediction task on three real-world datasets, generated by live video streaming events.
1 code implementation • 10 Nov 2020 • Zekarias T. Kefato, Sarunas Girdzijauskas, Nasrullah Sheikh, Alberto Montresor
In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention.
no code implementations • 12 Oct 2020 • Simone Zamboni, Zekarias Tilahun Kefato, Sarunas Girdzijauskas, Noren Christoffer, Laura Dal Col
In this work, we propose a new approach to pedestrian trajectory prediction, with the introduction of a novel 2D convolutional model.
1 code implementation • 30 Mar 2020 • Zekarias T. Kefato, Sarunas Girdzijauskas
In this study we show that in-order to extract high-quality context-sensitive node representations it is not needed to rely on supplementary node features, nor to employ computationally heavy and complex models.
1 code implementation • 28 Jan 2020 • Zekarias T. Kefato, Sarunas Girdzijauskas
Network representation learning (NRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and sparse graphs.