no code implementations • 22 Jun 2023 • Eleni Giovanoudi, Dimitrios Rafailidis
Compared with the other CDR loops, that is the H1 and H2 loops, the CDR structure of the H3 loop is more challenging due to its varying length and flexible structure.
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 • 31 Jul 2021 • Stefanos Antaris, Dimitrios Rafailidis
This might limit the recommendation accuracy, as in practice users follow different trends on the sequential recommendations.
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 • 18 Jun 2021 • Stefanos Antaris, Dimitrios Rafailidis, Romina Arriaza
Nowadays, live video streaming events have become a mainstay in viewer's communication in large international enterprises.
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 • 11 Nov 2020 • Stefanos Antaris, Dimitrios Rafailidis
We propose VStreamDRLS, a graph neural network architecture with a self-attention mechanism to capture the evolution of the graph structure of live video streaming events.
1 code implementation • 11 Nov 2020 • Stefanos Antaris, Dimitrios Rafailidis
In this study we propose Distill2Vec, a knowledge distillation strategy to train a compact model with a low number of trainable parameters, so as to reduce the latency of online inference and maintain the model accuracy high.
no code implementations • 11 Nov 2020 • Dimitrios Rafailidis, Stefanos Antaris
The main drawback of deep reinforcement strategies is that are based on predefined and fixed neural architectures.
no code implementations • 10 Nov 2020 • Stefanos Antaris, Dimitrios Rafailidis, Mohammad Aliannejadi
Conversational recommendation systems have recently gain a lot of attention, as users can continuously interact with the system over multiple conversational turns.
no code implementations • 16 Sep 2019 • Mohammad Aliannejadi, Dimitrios Rafailidis, Fabio Crestani
In this article, we propose a two-phase CR algorithm that incorporates the geographical influence of POIs and is regularized based on the variance of POIs popularity and users' activities over time.
no code implementations • 11 Aug 2019 • Dimitrios Rafailidis
In our model, we learn the embedding space with translation vectors and capture high-order feature interactions in users' multiple preferences across domains.
no code implementations • 29 Jun 2019 • Dimitrios Rafailidis, Gerhard Weiss
Furthermore, we study the effect of the proposed social behavioral attention mechanism and show that it is a key factor to our model's performance.
no code implementations • 29 Jun 2019 • Dimitrios Rafailidis, Gerhard Weiss
In this paper, we propose an adaptive deep learning strategy for cross-domain recommendation, referred to as ADC.
no code implementations • 31 May 2019 • Dimitrios Rafailidis
We show that our deep learning strategy plays an important role in capturing the nonlinear correlations between user preferences and the social information of trust and distrust relationships, and demonstrate the importance of our social negative sampling strategy on the proposed model.