2 code implementations • 2 Apr 2024 • Junchen Fu, Xuri Ge, Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Jie Wang, Joemon M. Jose
This is also a notable improvement over the Adapter and LoRA, which require 37-39 GB GPU memory and 350-380 seconds per epoch for training.
no code implementations • 25 Mar 2024 • Jie Wang, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose
The LE is learned from a subset of user-item interaction data, thus reducing the need for large training data, and can synthesise user feedback for offline data by: (i) acting as a state model that produces high quality states that enrich the user representation, and (ii) functioning as a reward model to accurately capture nuanced user preferences on actions.
no code implementations • 8 Feb 2024 • Konstantinos Zacharopoulos, Georgios Koutroumpas, Ioannis Arapakis, Konstantinos Georgopoulos, Javad Khangosstar, Sotiris Ioannidis
The cellular network plays a pivotal role in providing Internet access, since it is the only global-scale infrastructure with ubiquitous mobility support.
no code implementations • 26 Feb 2023 • Ioannis Arapakis, Panagiotis Papadopoulos, Kleomenis Katevas, Diego Perino
Distributed (or Federated) learning enables users to train machine learning models on their very own devices, while they share only the gradients of their models usually in a differentially private way (utility loss).
no code implementations • 5 Nov 2021 • Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose
However, the direct use of RL algorithms in the RS setting is impractical due to challenges like off-policy training, huge action spaces and lack of sufficient reward signals.
no code implementations • 28 Oct 2021 • Dusan Stamenkovic, Alexandros Karatzoglou, Ioannis Arapakis, Xin Xin, Kleomenis Katevas
The proposed SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations.
Multi-Objective Reinforcement Learning reinforcement-learning +2
no code implementations • 5 Mar 2021 • Paula Gómez Duran, Alexandros Karatzoglou, Jordi Vitrià, Xin Xin, Ioannis Arapakis
In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures.
1 code implementation • 22 Jan 2021 • Luis A. Leiva, Ioannis Arapakis, Costas Iordanou
This paper aims to stir debate about a disconcerting privacy issue on web browsing that could easily emerge because of unethical practices and uncontrolled use of technology.
no code implementations • 22 Jan 2021 • Ioannis Arapakis, Souneil Park, Martin Pielot
Traditionally, the efficiency and effectiveness of search systems have both been of great interest to the information retrieval community.
1 code implementation • 22 Jan 2021 • Lukas Brückner, Ioannis Arapakis, Luis A. Leiva
Most successful search queries do not result in a click if the user can satisfy their information needs directly on the SERP.
no code implementations • 10 Jun 2020 • Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose
A major component of RL approaches is to train the agent through interactions with the environment.
1 code implementation • 30 May 2020 • Ioannis Arapakis, Luis A. Leiva
Tracking mouse cursor movements can be used to predict user attention on heterogeneous page layouts like SERPs.
1 code implementation • 9 Apr 2020 • Xin Xin, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose
Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency.
no code implementations • 21 Jan 2020 • Ioannis Arapakis, Antonio Penta, Hideo Joho, Luis A. Leiva
There is thus an opportunity to devise a more effective ad pricing paradigm, in which ads are paid only if they are actually noticed.
3 code implementations • 15 Aug 2018 • Fajie Yuan, Alexandros Karatzoglou, Ioannis Arapakis, Joemon M. Jose, Xiangnan He
Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation.