no code implementations • 22 May 2023 • Xinchi Qiu, Ilias Leontiadis, Luca Melis, Alex Sablayrolles, Pierre Stock
In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference.
1 code implementation • 26 Jan 2023 • Maximilian Lam, Jeff Johnson, Wenjie Xiong, Kiwan Maeng, Udit Gupta, Yang Li, Liangzhen Lai, Ilias Leontiadis, Minsoo Rhu, Hsien-Hsin S. Lee, Vijay Janapa Reddi, Gu-Yeon Wei, David Brooks, G. Edward Suh
Together, for various on-device ML applications such as recommendation and language modeling, our system on a single V100 GPU can serve up to $100, 000$ queries per second -- a $>100 \times$ throughput improvement over a CPU-based baseline -- while maintaining model accuracy.
no code implementations • 7 Jun 2022 • Meisam Hejazinia Dzmitry Huba, Ilias Leontiadis, Kiwan Maeng, Mani Malek, Luca Melis, Ilya Mironov, Milad Nasr, Kaikai Wang, Carole-Jean Wu
Despite FL's initial success, many important deep learning use cases, such as ranking and recommendation tasks, have been limited from on-device learning.
no code implementations • 28 Sep 2021 • Mario Almeida, Stefanos Laskaridis, Abhinav Mehrotra, Lukasz Dudziak, Ilias Leontiadis, Nicholas D. Lane
To this end, we analyse over 16k of the most popular apps in the Google Play Store to characterise their DNN usage and performance across devices of different capabilities, both across tiers and generations.
no code implementations • 21 Jun 2021 • Stylianos I. Venieris, Ioannis Panopoulos, Ilias Leontiadis, Iakovos S. Venieris
Collectively, these results highlight the critical need for further exploration as to how the various cross-stack solutions can be best combined in order to bring the latest advances in deep learning close to users, in a robust and efficient manner.
no code implementations • 20 Apr 2021 • Mario Almeida, Stefanos Laskaridis, Stylianos I. Venieris, Ilias Leontiadis, Nicholas D. Lane
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs).
2 code implementations • NeurIPS 2021 • Samuel Horvath, Stefanos Laskaridis, Mario Almeida, Ilias Leontiadis, Stylianos I. Venieris, Nicholas D. Lane
FjORD alleviates the problem of client system heterogeneity by tailoring the model width to the client's capabilities.
no code implementations • 2 Feb 2021 • Ilias Leontiadis, Stefanos Laskaridis, Stylianos I. Venieris, Nicholas D. Lane
On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques.
no code implementations • 14 Aug 2020 • Stefanos Laskaridis, Stylianos I. Venieris, Mario Almeida, Ilias Leontiadis, Nicholas D. Lane
Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices.
2 code implementations • 12 Apr 2020 • Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas, Soteris Demetriou, Ilias Leontiadis, Andrea Cavallaro, Hamed Haddadi
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs).
no code implementations • 20 Jul 2019 • Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Athena Vakali, Nicolas Kourtellis
We also explore specific manifestations of abusive behavior, i. e., cyberbullying and cyberaggression, in one of the hate-related communities (Gamergate).
no code implementations • 17 May 2019 • Mario Almeida, Stefanos Laskaridis, Ilias Leontiadis, Stylianos I. Venieris, Nicholas D. Lane
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring.
1 code implementation • 24 Apr 2019 • Harris Partaourides, Kostantinos Papadamou, Nicolas Kourtellis, Ilias Leontiadis, Sotirios Chatzis
Modern deep learning approaches have achieved groundbreaking performance in modeling and classifying sequential data.
no code implementations • 30 Aug 2018 • Kleomenis Katevas, Katrin Hänsel, Richard Clegg, Ilias Leontiadis, Hamed Haddadi, Laurissa Tokarchuk
Remembering our day-to-day social interactions is challenging even if you aren't a blue memory challenged fish.
no code implementations • 1 Feb 2018 • Antigoni-Maria Founta, Despoina Chatzakou, Nicolas Kourtellis, Jeremy Blackburn, Athena Vakali, Ilias Leontiadis
Hate speech, offensive language, sexism, racism and other types of abusive behavior have become a common phenomenon in many online social media platforms.
7 code implementations • 1 Feb 2018 • Antigoni-Maria Founta, Constantinos Djouvas, Despoina Chatzakou, Ilias Leontiadis, Jeremy Blackburn, Gianluca Stringhini, Athena Vakali, Michael Sirivianos, Nicolas Kourtellis
In recent years, offensive, abusive and hateful language, sexism, racism and other types of aggressive and cyberbullying behavior have been manifesting with increased frequency, and in many online social media platforms.
Social and Information Networks 68T06 K.4.2
no code implementations • 19 Dec 2017 • Kleomenis Katevas, Ilias Leontiadis, Martin Pielot, Joan Serrà
Besides using classical gradient-boosted trees, we demonstrate how to make continual predictions using a recurrent neural network (RNN).
Human-Computer Interaction
no code implementations • WS 2017 • Joan Serr{\`a}, Ilias Leontiadis, Dimitris Spathis, Gianluca Stringhini, Jeremy Blackburn, Athena Vakali
Common approaches to text categorization essentially rely either on n-gram counts or on word embeddings.
no code implementations • 17 May 2017 • Kleomenis Katevas, Ilias Leontiadis, Martin Pielot, Joan Serrà
We present a practical approach for processing mobile sensor time series data for continual deep learning predictions.
no code implementations • 18 Apr 2017 • Joan Serrà, Ilias Leontiadis, Alexandros Karatzoglou, Konstantina Papagiannaki
Our results indicate that, compared to the best baseline, tree-based models can deliver up to 14% better forecasts for regular hot spots and 153% better forecasts for non-regular hot spots.
no code implementations • 26 Jun 2014 • Chloë Brown, Christos Efstratiou, Ilias Leontiadis, Daniele Quercia, Cecilia Mascolo, James Scott, Peter Key
The layouts of the buildings we live in shape our everyday lives.
Computers and Society Human-Computer Interaction Social and Information Networks