Overview
Deep networks have shown outstanding scaling properties both in terms of data and model sizes: larger performs better. Unfortunately, the computational cost of current state-of-the-art methods is prohibitive. A number of new techniques have recently arisen to address and improve this fundamental quality-cost trade-off. Methods like conditional computation, adaptive computation, dynamic model sparsification, and early-exit approaches aim to address the above mentioned quality-cost trade off. This workshop explores such exciting and practically-relevant research avenues. As part of contributed content we will invite high-quality papers on the following topics: dynamic routing, mixture-of-experts models, early-exit methods, conditional computations, capsules and object-oriented learning, reusable components, online network growing and pruning, online neural architecture search and applications of dynamic networks (continual learning, wireless/embedded devices and similar topics).
The 1st Dynamic Neural Networks workshop will be a hybrid workshop at ICML 2022 on July 22, 2022. Our goal is to advance the general discussion of the topic by highlighting contributions proposing innovative approaches regarding dynamic neural networks.
Announcements
- The recording of our workshop is available now!
- Workshop schedule is announced!
- Accepted papers (poster and oral presentations) are announced. Congratulations to all authors!
- Microsoft CMT Submission portal is now open!
Submission Deadline: May 31, 2022 (Anywhere on Earth)
Author Notification: June 13, 2022
Video Deadline: June 28th, 2022
Camera Ready Deadline: July 9, 2022
Workshop Day: July 22, 2022
Speakers (More Info)
Invited Speakers
Organizers
Panel Chairs
Program Committee
- Canwen Xu, UC San Diego
- Yigitcan Kaya, University of Maryland
- Maciej Wolczyk, Jagiellonian University
- Bartosz Wojcik, Jagiellonian University
- Yoshitomo Matsubara, Amazon Alexa AI
- Thomas Verelst, KU Leuven
Reviewers
- Alessio Devoto, Sapienza Università di Roma
- Alessio Verdone, La Sapienza
- André Susano Pinto, Google Research
- Andrea Bacciu, Sapienza University of Rome
- Andrea Mastropietro, Sapienza University of Rome
- Andreas Steiner, Google Brain
- Bartosz Wójcik, Jagiellonian University
- Bartosz Zieliński, Jagiellonian University
- Basil Mustafa, Google
- Battista Biggio, University of Cagliari
- Canwen Xu, UC San Diego
- Claudio Gallicchio, University of Pisa
- Daniel Marczak, Warsaw University of Technology
- Fabrizio Silvestri, Sapienza
- Filip Szatkowski, Warsaw University of Technology
- Giulia Cassarà, Sapienza University of Rome
- Ilya Tolstikhin, Google
- Indro Spinelli, Sapienza University of Rome
- Irene Tallini, Sapienza University of Rome
- Jary Pomponi, Università di Roma Sapienza
- Jieyu Lin, University of Toronto
- Joan Puigcerver, Google
- Kamil Deja, Warsaw University of Technology
- Karol Piczak, Jagiellonian University
- Konrad Cop, Warsaw University of Technology
- Lev Telyatnikov, Sapienza University
- Maciej Szymkowski, Warsaw University of Technology
- Maciej Wołczyk, Jagiellonian University
- Maciej Zieba, Wroclaw University of Science and Technology
- Manuel Roveri, Politecnico di Milano
- Massimo Panella, University of Rome Sapienza
- Mateusz Ostaszewski, Institute of Theoretical and Applied Informatics
- Michał Bortkiewicz, Warsaw University of Technology
- Michał Sadowski, Jagiellonian University
- Michele Scarpiniti, Sapienza University of Rome
- Mohanad Odema, University of California Irvine
- Monika Wysoczańska, Warsaw University of Technology
- Paweł Wawrzyński, Warsaw University of Technology
- Philippe Tillet, OpenAI
- Przemysław Spurek, Jagiellonian University
- Sai Qian Zhang, Harvard University
- Stanislaw Pawlak, Warsaw University of Technology
- Surat Teerapittayanon, Harvard University
- Thomas Unterthiner, Google Research
- Thomas Verelst, KU Leuven
- Utku Evci, Google
- Valerio Marsocci, Sapienza University of Rome
- Witold Oleszkiewicz, Warsaw University of Technology
- Wojciech Masarczyk, Warsaw University of Technology
- Xin Dong, Harvard Univeristy
- Yigitcan Kaya, University of Maryland
Contact: icmldynamicnn@gmail.com