Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Erwan Le Merrer"'
Partitioning an input graph over a set of workers is a complex operation. Objectives are twofold: split the work evenly, so that every worker gets an equal share, and minimize edge cut to achieve a good work locality (i.e. workers can work independen
Externí odkaz:
http://arxiv.org/abs/1310.8211
Publikováno v:
ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5de16d82fba0bfa7b51c3a7a283b8a2a
https://doi.org/10.1109/icassp43922.2022.9746293
https://doi.org/10.1109/icassp43922.2022.9746293
Algorithmic decision making is now widespread, ranging from health care allocation to more common actions such as recommendation or information ranking. The aim to audit these algorithms has grown alongside. In this paper, we focus on external audits
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8084e511b7a22cff172119f62d9e6f70
https://inria.hal.science/hal-03583919
https://inria.hal.science/hal-03583919
Publikováno v:
CVPR
CVPR 2021-Conference on Computer Vision and Pattern Recognition
CVPR 2021-Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtual, France. pp.10430--10439
CVPR 2021-Conference on Computer Vision and Pattern Recognition
CVPR 2021-Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtual, France. pp.10430--10439
Machine learning classifiers are critically prone to evasion attacks. Adversarial examples are slightly modified inputs that are then misclassified, while remaining perceptively close to their originals. Last couple of years have witnessed a striking
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5760306501d54b15158d08e7dded8645
https://doi.org/10.1109/cvpr46437.2021.01029
https://doi.org/10.1109/cvpr46437.2021.01029
Publikováno v:
ICIP 2021-IEEE International Conference on Image Processing
ICIP 2021-IEEE International Conference on Image Processing, Sep 2021, Anchorage, Alaska, United States. pp.1-5, ⟨10.1109/ICIP42928.2021.9506053⟩
ICIP 2021-IEEE International Conference on Image Processing, Sep 2021, Anchorage, Alaska, United States. pp.1-5, ⟨10.1109/ICIP42928.2021.9506053⟩
Many defenses have emerged with the development of adversarial attacks. Models must be objectively evaluated accordingly. This paper systematically tackles this concern by proposing a new parameter-free benchmark we coin RoBIC. RoBIC fairly evaluates
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::738c550393f84f13f555ed54a9b99af5
http://arxiv.org/abs/2102.05368
http://arxiv.org/abs/2102.05368
Autor:
Adel Jaouen, Erwan Le Merrer
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030894528
The training of deep neural network classifiers results in decision boundaries whose geometry is still not well understood. This is in direct relation with classification problems such as so called corner case inputs. We introduce zoNNscan, an index
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::03536d7fa77aaac50eeeac2ef9303fa3
https://doi.org/10.1007/978-3-030-89453-5_3
https://doi.org/10.1007/978-3-030-89453-5_3
Publikováno v:
ACM/IFIP Middleware 2020-Annual ACM/IFIP Middleware conference
ACM/IFIP Middleware 2020-Annual ACM/IFIP Middleware conference, Dec 2020, Delft / Virtual, Netherlands. ⟨10.1145/3423211.3425688⟩
Middleware
Middleware 2020-ACM/IFIP Middleware
Middleware 2020-ACM/IFIP Middleware, Dec 2020, Virtual, Netherlands. pp.1-14
ACM/IFIP Middleware 2020-Annual ACM/IFIP Middleware conference, Dec 2020, Delft / Virtual, Netherlands. ⟨10.1145/3423211.3425688⟩
Middleware
Middleware 2020-ACM/IFIP Middleware
Middleware 2020-ACM/IFIP Middleware, Dec 2020, Virtual, Netherlands. pp.1-14
International audience; Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines, inducing signifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2deadf1d78940aaa263d8bd77b03a1fc
https://hal.science/hal-03118260/file/middleware2020-GGKLM-FeGAN-preprint.pdf
https://hal.science/hal-03118260/file/middleware2020-GGKLM-FeGAN-preprint.pdf
Autor:
Erwan Le Merrer, Gilles Trédan
Publikováno v:
Nature Machine Intelligence
Nature Machine Intelligence, Nature Research, 2020, 2 (9), pp.529-539. ⟨10.1038/s42256-020-0216-z⟩
Nature Machine Intelligence, 2020, 2 (9), pp.529-539. ⟨10.1038/s42256-020-0216-z⟩
Nature Machine Intelligence, Nature Research, 2020, 2 (9), pp.529-539. ⟨10.1038/s42256-020-0216-z⟩
Nature Machine Intelligence, 2020, 2 (9), pp.529-539. ⟨10.1038/s42256-020-0216-z⟩
The concept of explainability is envisioned to satisfy society’s demands for transparency about machine learning decisions. The concept is simple: like humans, algorithms should explain the rationale behind their decisions so that their fairness ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::49e278ffacacbe370f1852987939461c
https://hal.laas.fr/hal-03048809/document
https://hal.laas.fr/hal-03048809/document
Autor:
Tredan Gilles, Erwan Le Merrer
Publikováno v:
ISSRE 2019-IEEE 30th International Symposium on Software Reliability Engineering
ISSRE 2019-IEEE 30th International Symposium on Software Reliability Engineering, Oct 2019, Berlin, Germany. pp.1-11, ⟨10.1109/ISSRE.2019.00049⟩
ISSRE
ISSRE 2019-IEEE 30th International Symposium on Software Reliability Engineering, Oct 2019, Berlin, Germany. pp.1-11, ⟨10.1109/ISSRE.2019.00049⟩
ISSRE
Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets can be tr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::588b2bfcd4c920ff8946d5992b53c39e
https://hal.science/hal-02268136
https://hal.science/hal-02268136
Autor:
Gilles Tredan, Erwan Le Merrer
Publikováno v:
MASCOTS 2019-27th IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems
MASCOTS 2019-27th IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Oct 2019, Rennes, France. pp.235-240, ⟨10.1109/MASCOTS.2019.00033⟩
MASCOTS
MASCOTS 2019-27th IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, Oct 2019, Rennes, France. pp.235-240, ⟨10.1109/MASCOTS.2019.00033⟩
MASCOTS
Modern online applications value real-time queries over fresh data models. This is the case for graph-based applications, such as social networking or recommender systems, running on front-end servers in production. A core problem in graph processing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::75002f9b3017480db79bdb3cd876052a
https://hal.science/hal-02193594/document
https://hal.science/hal-02193594/document