Zobrazeno 1 - 10
of 8 161
pro vyhledávání: '"Kertesz, A"'
Publikováno v:
IEEE Access (2024) 96017-96050
In recent years, large language models (LLMs) have achieved remarkable success in natural language processing (NLP). LLMs require an extreme amount of parameters to attain high performance. As models grow into the trillion-parameter range, computatio
Externí odkaz:
http://arxiv.org/abs/2409.04833
Poverty map inference has become a critical focus of research, utilizing both traditional and modern techniques, ranging from regression models to convolutional neural networks applied to tabular data, satellite imagery, and networks. While much atte
Externí odkaz:
http://arxiv.org/abs/2408.01631
Members of a society can be characterized by a large number of features, such as gender, age, ethnicity, religion, social status, and shared activities. One of the main tie-forming factors between individuals in human societies is homophily, the tend
Externí odkaz:
http://arxiv.org/abs/2405.03080
Autor:
Palmieri, Luigi, Boldrini, Chiara, Valerio, Lorenzo, Passarella, Andrea, Conti, Marco, Kertész, János
In the vibrant landscape of AI research, decentralised learning is gaining momentum. Decentralised learning allows individual nodes to keep data locally where they are generated and to share knowledge extracted from local data among themselves throug
Externí odkaz:
http://arxiv.org/abs/2405.02377
Autor:
Zhu, Manran, Kertész, János
Data deluge characteristic for our times has led to information overload, posing a significant challenge to effectively finding our way through the digital landscape. Addressing this issue requires an in-depth understanding of how we navigate through
Externí odkaz:
http://arxiv.org/abs/2404.06591
The structure of personal networks reflects how we organise and maintain social relationships. The distribution of tie strengths in personal networks is heterogeneous, with a few close, emotionally intense relationships and a larger number of weaker
Externí odkaz:
http://arxiv.org/abs/2403.19529
Fully decentralised federated learning enables collaborative training of individual machine learning models on a distributed network of communicating devices while keeping the training data localised on each node. This approach avoids central coordin
Externí odkaz:
http://arxiv.org/abs/2403.15855
Cascades are self-reinforcing processes underlying the systemic risk of many complex systems. Understanding the universal aspects of these phenomena is of fundamental interest, yet typically bound to numerical observations in ad-hoc models and limite
Externí odkaz:
http://arxiv.org/abs/2401.09313
Autor:
Bonamassa, I., Ráth, B., Pósfai, M., Abért, M., Keliger, D., Szegedy, B., Kertész, J., Lovász, L., Barabási, A. -L.
In physical networks, like the brain or metamaterials, we often observe local bundles, corresponding to locally aligned link configurations. Here we introduce a minimal model for bundle formation, modeling physical networks as non-equilibrium packing
Externí odkaz:
http://arxiv.org/abs/2401.02579
Autor:
Valerio, Lorenzo, Boldrini, Chiara, Passarella, Andrea, Kertész, János, Karsai, Márton, Iñiguez, Gerardo
Federated Learning (FL) is a well-known framework for successfully performing a learning task in an edge computing scenario where the devices involved have limited resources and incomplete data representation. The basic assumption of FL is that the d
Externí odkaz:
http://arxiv.org/abs/2312.04504