Zobrazeno 1 - 10
of 19
pro vyhledávání: '"de Gusmão, Pedro Porto Buarque"'
Autor:
Lau, Kin Wai, Rehman, Yasar Abbas Ur, de Gusmão, Pedro Porto Buarque, Po, Lai-Man, Ma, Lan, Xie, Yuyang
Federated Learning (FL) has emerged as a privacy-preserving method for training machine learning models in a distributed manner on edge devices. However, on-device models face inherent computational power and memory limitations, potentially resulting
Externí odkaz:
http://arxiv.org/abs/2409.15898
Autor:
Rehman, Yasar Abbas Ur, Gao, Yan, de Gusmão, Pedro Porto Buarque, Alibeigi, Mina, Shen, Jiajun, Lane, Nicholas D.
The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge. The integration of self-supervised learning (SSL) and federated learning (FL) into one coherent system can potentially offer data priv
Externí odkaz:
http://arxiv.org/abs/2307.07393
Autor:
Sani, Lorenzo, de Gusmão, Pedro Porto Buarque, Iacob, Alex, Zhao, Wanru, Qiu, Xinchi, Gao, Yan, Fernandez-Marques, Javier, Lane, Nicholas Donald
Federated Learning (FL) is a privacy-focused machine learning paradigm that collaboratively trains models directly on edge devices. Simulation plays an essential role in FL adoption, helping develop novel aggregation and client sampling strategies. H
Externí odkaz:
http://arxiv.org/abs/2306.17453
Autor:
Valadi, Viktor, Qiu, Xinchi, de Gusmão, Pedro Porto Buarque, Lane, Nicholas D., Alibeigi, Mina
Federated learning (FL) systems are susceptible to attacks from malicious actors who might attempt to corrupt the training model through various poisoning attacks. FL also poses new challenges in addressing group bias, such as ensuring fair performan
Externí odkaz:
http://arxiv.org/abs/2306.04040
Autor:
Qiu, Xinchi, Pan, Heng, Zhao, Wanru, Ma, Chenyang, de Gusmão, Pedro Porto Buarque, Lane, Nicholas D.
The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently. However, in many interesting problems
Externí odkaz:
http://arxiv.org/abs/2305.11236
Autor:
Rehman, Yasar Abbas Ur, Gao, Yan, Shen, Jiajun, de Gusmao, Pedro Porto Buarque, Lane, Nicholas
The ubiquity of camera-enabled mobile devices has lead to large amounts of unlabelled video data being produced at the edge. Although various self-supervised learning (SSL) methods have been proposed to harvest their latent spatio-temporal representa
Externí odkaz:
http://arxiv.org/abs/2207.01975
Federated Learning (FL) allows parties to learn a shared prediction model by delegating the training computation to clients and aggregating all the separately trained models on the server. To prevent private information being inferred from local mode
Externí odkaz:
http://arxiv.org/abs/2205.06117
Autor:
Mathur, Akhil, Beutel, Daniel J., de Gusmão, Pedro Porto Buarque, Fernandez-Marques, Javier, Topal, Taner, Qiu, Xinchi, Parcollet, Titouan, Gao, Yan, Lane, Nicholas D.
Publikováno v:
On-device Intelligence Workshop at the Fourth Conference on Machine Learning and Systems (MLSys), April 9, 2021
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store data in the cloud. Despite th
Externí odkaz:
http://arxiv.org/abs/2104.03042
Autor:
Qiu, Xinchi, Parcollet, Titouan, Fernandez-Marques, Javier, de Gusmao, Pedro Porto Buarque, Gao, Yan, Beutel, Daniel J., Topal, Taner, Mathur, Akhil, Lane, Nicholas D.
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers. In response, alternatives to centralized training such as Federated L
Externí odkaz:
http://arxiv.org/abs/2102.07627
Autor:
Beutel, Daniel J., Topal, Taner, Mathur, Akhil, Qiu, Xinchi, Fernandez-Marques, Javier, Gao, Yan, Sani, Lorenzo, Li, Kwing Hei, Parcollet, Titouan, de Gusmão, Pedro Porto Buarque, Lane, Nicholas D.
Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to
Externí odkaz:
http://arxiv.org/abs/2007.14390