Distributed AI for REsource-Constrained Platforms (DARE) Workshop
Short: 1st DARE
- Luis Almeida – CISTER / University of Porto, Portugal
- Veselka Boeva – Blekinge Institute of Technology, Sweden
- Emiliano Casalicchio – Blekinge Institute of Technology, Sweden
- Nicolás González-Deleito – Sirris, Belgium
- Anna Hristoskova – Sirris, Belgium
- Pedro Santos – CISTER / Polytechnic of Porto, Portugal
- Joana Sousa – NOS Inovação, Portugal
- Barış Bulut, Enforma Bilişim A.Ş, Turkey
The standard approach explored by IoT applications of leveraging cloud computing to address constraints at the level of end and edge nodes is no longer viable, especially for applications with hard real-time requirements and increasing AI usage. Managing the complexity and heterogeneity of IoT systems is a big challenge for the future of edge computing as data is collected and analysed on a large network of different devices which may change at run-time. Only with an open and technology-agnostic approach this challenge can be addressed for a broad set of applications.
In addition, an edge computing system can maintain its function without access to a centralized infrastructure. With application services and tasks deployed on local resources, network problems will become less critical. At the same time, as data becomes more valuable, security and privacy concerns will play an important role. In a networked IoT system, a single vulnerable device can be an entry point for cyberattacks.
This workshop will focus on AI and ML techniques, edge computing systems, and security and privacy in view of data sharing in order to enable the smart and sustainable planning and operation of resource constrained IoT and edge computing applications. The workshop is organized within the scope of the ITEA3 MIRAI project (https://itea3.org/project/mirai.html).
The DARE workshop welcomes innovative contributions, early results and position papers related to the topics listed below, and intends to foster informal discussions and cross-fertilization on the convergence of AI and edge computing. Contributions should address one or more of the following topics:
- Open and interoperable ad-hoc architectures for on-demand computation
- Scalability of edge/fog computing IoT applications
- Run-time adaptation of edge/fog computing infrastructures
- Advanced AI algorithms and techniques for continual and evolving learning
- Distributed and composable ML models and techniques guaranteeing high-quality decision-making
- Security and privacy on the edge including secure data sharing between edge nodes
- Low-latency IoT applications deployment and operation on edge computing platforms
- Benchmarking of AI solutions for edge computing
- Industrial experiences/show cases for AI enabled edge computing platform management, orchestration, operation
- Industrial experiences/show cases of distributed AI applications running on edge computing infrastructures
- Real-world implementations of on-demand computation infrastructures
- Development/refinement of AI/ML algorithms to execute in resource-constrained devices
- Distributed management/orchestration of IoT applications at edge infrastructure
Initial submissions for the DARE workshop will be received through AIAI 2021 submission system. Authors will be able to select “submit to DARE Workshop” option after logging in.
How to submit a contribution
All papers should be submitted either in a doc/docx or in a pdf form and will be peer reviewed by at least 2 academic referees. Contributing authors must follow the AIAI2021’s paper format guidelines as far as the IFIP AICT file format.
Submission site: https://www.easyacademia.org/aiai2021