Zobrazeno 1 - 10
of 90 438
pro vyhledávání: '"Kay, P."'
Cross-project defect prediction (CPDP) leverages machine learning (ML) techniques to proactively identify software defects, especially where project-specific data is scarce. However, developing a robust ML pipeline with optimal hyperparameters that e
Externí odkaz:
http://arxiv.org/abs/2411.06491
In this survey, we introduce Meta-Black-Box-Optimization (MetaBBO) as an emerging avenue within the Evolutionary Computation (EC) community, which incorporates Meta-learning approaches to assist automated algorithm design. Despite the success of Meta
Externí odkaz:
http://arxiv.org/abs/2411.00625
Latent diffusion models have become the popular choice for scaling up diffusion models for high resolution image synthesis. Compared to pixel-space models that are trained end-to-end, latent models are perceived to be more efficient and to produce hi
Externí odkaz:
http://arxiv.org/abs/2410.19324
Offloading computationally expensive algorithms to the edge or even cloud offers an attractive option to tackle limitations regarding on-board computational and energy resources of robotic systems. In cloud-native applications deployed with the conta
Externí odkaz:
http://arxiv.org/abs/2410.18825
Autor:
Sereno, Mauro, Maurogordato, Sophie, Cappi, Alberto, Barrena, Rafael, Benoist, Christophe, Haines, Christopher P., Radovich, Mario, Nonino, Mario, Ettori, Stefano, Ferragamo, Antonio, Gavazzi, Raphael, Huot, Sophie, Pizzuti, Lorenzo, Pratt, Gabriel W., Streblyanska, Alina, Zarattini, Stefano, Castignani, Gianluca, Eckert, Dominique, Gastaldello, Fabio, Kay, Scott T., Lovisari, Lorenzo, Maughan, Ben J., Pointecouteau, Etienne, Rasia, Elena, Rossetti, Mariachiara, Sayers, Jack
The Cluster HEritage project with XMM-Newton - Mass Assembly and Thermodynamics at the Endpoint of structure formation (CHEX-MATE) is a programme to study a minimally biased sample of 118 galaxy clusters detected by Planck through the Sunyaev-Zeldovi
Externí odkaz:
http://arxiv.org/abs/2410.18165
Recent advancements in Large Language Models (LLMs) have positioned them as powerful tools for clinical decision-making, with rapidly expanding applications in healthcare. However, concerns about bias remain a significant challenge in the clinical im
Externí odkaz:
http://arxiv.org/abs/2410.16574
How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify know
Externí odkaz:
http://arxiv.org/abs/2410.16386
Autor:
Riva, G., Pratt, G. W., Rossetti, M., Bartalucci, I., Kay, S. T., Rasia, E., Gavazzi, R., Umetsu, K., Arnaud, M., Balboni, M., Bonafede, A., Bourdin, H., De Grandi, S., De Luca, F., Eckert, D., Ettori, S., Gaspari, M., Gastaldello, F., Ghirardini, V., Ghizzardi, S., Gitti, M., Lovisari, L., Maughan, B. J., Mazzotta, P., Molendi, S., Pointecouteau, E., Sayers, J., Sereno, M., Towler, I.
We characterise the entropy profiles of 32 very high mass ($M_{500}>7.75\times10^{14}~M_{\odot}$) galaxy clusters (HIGHMz), selected from the CHEX-MATE sample, to study the intracluster medium (ICM) entropy distribution in a regime where non-gravitat
Externí odkaz:
http://arxiv.org/abs/2410.11947
Graph self-training is a semi-supervised learning method that iteratively selects a set of unlabeled data to retrain the underlying graph neural network (GNN) model and improve its prediction performance. While selecting highly confident nodes has pr
Externí odkaz:
http://arxiv.org/abs/2410.09348
Autor:
Yao, Yuhang, Li, Yuan, Fan, Xinyi, Li, Junhao, Liu, Kay, Jin, Weizhao, Ravi, Srivatsan, Yu, Philip S., Joe-Wong, Carlee
Federated graph learning is an emerging field with significant practical challenges. While many algorithms have been proposed to enhance the accuracy of training graph neural networks, e.g., for node classification problems on large graphs, in a fede
Externí odkaz:
http://arxiv.org/abs/2410.06340