Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Diskin, Michael"'
Node classification is a classical graph machine learning task on which Graph Neural Networks (GNNs) have recently achieved strong results. However, it is often believed that standard GNNs only work well for homophilous graphs, i.e., graphs where edg
Externí odkaz:
http://arxiv.org/abs/2302.11640
Many deep learning applications benefit from using large models with billions of parameters. Training these models is notoriously expensive due to the need for specialized HPC clusters. In this work, we consider alternative setups for training large
Externí odkaz:
http://arxiv.org/abs/2301.11913
Autor:
Borzunov, Alexander, Ryabinin, Max, Dettmers, Tim, Lhoest, Quentin, Saulnier, Lucile, Diskin, Michael, Jernite, Yacine, Wolf, Thomas
The infrastructure necessary for training state-of-the-art models is becoming overly expensive, which makes training such models affordable only to large corporations and institutions. Recent work proposes several methods for training such models col
Externí odkaz:
http://arxiv.org/abs/2207.03481
Variational inequalities in general and saddle point problems in particular are increasingly relevant in machine learning applications, including adversarial learning, GANs, transport and robust optimization. With increasing data and problem sizes ne
Externí odkaz:
http://arxiv.org/abs/2110.03313
Many areas of deep learning benefit from using increasingly larger neural networks trained on public data, as is the case for pre-trained models for NLP and computer vision. Training such models requires a lot of computational resources (e.g., HPC cl
Externí odkaz:
http://arxiv.org/abs/2106.11257
Autor:
Diskin, Michael, Bukhtiyarov, Alexey, Ryabinin, Max, Saulnier, Lucile, Lhoest, Quentin, Sinitsin, Anton, Popov, Dmitry, Pyrkin, Dmitry, Kashirin, Maxim, Borzunov, Alexander, del Moral, Albert Villanova, Mazur, Denis, Kobelev, Ilia, Jernite, Yacine, Wolf, Thomas, Pekhimenko, Gennady
Modern deep learning applications require increasingly more compute to train state-of-the-art models. To address this demand, large corporations and institutions use dedicated High-Performance Computing clusters, whose construction and maintenance ar
Externí odkaz:
http://arxiv.org/abs/2106.10207
Autor:
Gravador, Rufielyn S., Valentini, Valeria, Harrison, Sabine M., Fahey, Alan, Moloney, Aidan P., Diskin, Michael G., Monahan, Frank J.
Publikováno v:
In Small Ruminant Research November 2022 216
Autor:
López Corrales, Jesús, Cwiklinski, Krystyna *, De Marco Verissimo, Carolina, Dorey, Amber, Lalor, Richard, Jewhurst, Heather, McEvoy, Amanda, Diskin, Michael, Duffy, Catherine, Cosby, S. Louise, Keane, Orla M., Dalton, John Pius
Publikováno v:
In Veterinary Parasitology October 2021 298
Autor:
Randi, Federico, Kelly, Alan K., Parr, Mervyn H., Diskin, Michael G., Lively, Francis, Lonergan, Patrick, Kenny, David A.
Publikováno v:
In Theriogenology 15 September 2021 172:223-229
Autor:
Gkarane, Vasiliki, Brunton, Nigel P., Allen, Paul, Gravador, Rufielyn S., Claffey, Noel A., Diskin, Michael G., Fahey, Alan G., Farmer, Linda J., Moloney, Aidan P., Alcalde, Maria J., Murphy, Patrick, Monahan, Frank J.
Publikováno v:
In Food Research International January 2019 115:54-64