December 13-16, 2021, Pasadena, California, USA

Advanced Machine Learning and Applications: Federated Learning and Meta-Learning (AML-IoT FLAME 2021)


Special Session of ICMLA 2021

20TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS

ABOUT THE SPECIAL SESSION

This workshop focuses on how to address unique challenges during applying AI/ML in IoT. It invites researchers and practitioners to submit papers describing original work or experiences related to the entire life-cycle of an IoT powered by AI and ML, specifically federated learning and meta-learning. Federated learning and meta-learning techniques for IoT systems are the two main pivotal topics of this workshop. The uniqueness of our workshop is that it focuses on realistic problems that exist throughout the life-cycle of AI/ML-powered IoT. Many problems have not been well addressed in existing conferences or workshops. For example, most existing work only addresses how to develop good AI/ML models while assuming that a centralized dataset already exists. We hope to bridge this gap with our workshop. Also, most studies assume there exists a sufficient training dataset, while in real-world scenarios there are many limitations on available datasets.

CALL FOR PAPER

Artificial intelligence (AI) and machine learning (ML) are key enabling technologies for many Internet of Things (IoT) applications and meta-learning. However, the collection and processing of data for AI and ML is very challenging in the IoT domain, even learning from data is critical in meta-learning and federated learning. This special session aims to bring together researchers from such domains and topics for this workshop include, but are not limited to:

Topics of Interests

Techniques:

  1. Techniques for making use of data collected by geographically dispersed sensors to provide useful services through AI/ML

  2. Techniques for sharing data and training AI/ML models while preserving user sensitive information

  3. Techniques for dealing with noisy data and labels

  4. Techniques for reducing human effort in data labeling (such as active learning)

  5. Techniques for evolving from a new system that is initially trained with only a small amount of data

Learning paradigms:

  1. Automated Learning

  2. Meta-learning

  3. Efficient data analytics

  4. Distributed learning

  5. Federated learning and its applications

  6. Efficient learning on IoT devices

  7. Collaborative learning

Important Dates:

Submission Deadline: August 16, 2021

Notification of Acceptance: September 13, 2021

Camera-ready papers & Pre-Registration: October 11, 2021

Submission Guidelines and Instructions

Papers submitted for reviewing should conform to IEEE specifications. Manuscript templates can be downloaded from IEEE website. The maximum length of papers is 8 pages. All the papers will go through double-blind peer review process. Authors’ names and affiliations should not appear in the submitted paper. Authors’ prior work should be cited in the third person. Authors should also avoid revealing their identities and/or institutions in the text, figures, links, etc.

Papers must be submitted via the CMT System by selecting the track “Special Session on Advanced Machine Learning and Applications: Federated Learning and Meta-Learning”. All accepted papers must be presented by one of the authors, who must register. Detailed instructions for submitting papers can be found at How to Submit.

Paper Publication:

Accepted papers will be published in the ICMLA 2021 conference proceedings (to be published by IEEE).

Organizers

Workshop Chairs

M. Hadi Amini

Florida International University

Arash Gholami Davoodi

Apple

Technical Program Committee (Tentative; To be Updated)

Hamid Reza Arabnia

University of Georgia

Panos Pardalos

University of Florida

Mehdi Bennis

University of Oulu

Javad Heidari

LG Silicon Valley Lab

Praveen Palanisamy

Senior AI Engineer, Microsoft

Kin K. Leung

Imperial College

Mohammad Mozaffari

Ericsson Research

Mohammad Shaqfeh

Texas A&M University at Qatar

Javad Mohammadi

Carnegie Mellon University

Mingzhe Chen

Princeton University

Abbas Khosravi

Deakin University

Sakshi Mishra

University of British Columbia

Urmish Thakker

SambaNova Systems

Jihong Park

Deakin University

Parinaz Naghizadeh

The Ohio State University

Shahab Bahrami

The University of British Columbia

Vahid Akbari

University of Nottingham

Marzieh Khakifirooz

Tecnológico de Monterrey

Soheyla Amirian

University of Georgia

Mostafa Mirshekari

Stanford University

Victor Valls Delgado

Yale University

Farid Ghareh Mohammadi

University of Georgia

Ahmed Imteaj

Florida International University

Ali Tazarv

UC Irvine

Publicity Chairs:

Khandakar Mamun Ahmed

Florida International University

Farzan Shenavarmasouleh

University of Georgia

AGENDA

TBA

The Venue

The AML-IoT FLAME 2021 workshop is part of (co-located with) IEEE ICMLA2021, which will be held at Pasadena, California.