PDFL21: Parallel, Distributed, and Federated Learning 2021 virtual workshop at ECMLPKDD 2021 Bilbao, Spain, September 17, 2021 |
Conference website | https://pdfl.iais.fraunhofer.de/ |
Submission link | https://easychair.org/conferences/?conf=pdfl21 |
Submission deadline | June 23, 2021 |
Important Dates
- Submission deadline: 23 June 2021
- Acceptance notification: 23 July 2021
- Camera-ready deadline: 20 August 2021
- Workshop: TBA
Overview
In the past few years, as large data volumes are being generated on edge devices, such as mobile phones or autonomous vehicles, more and more machine learning systems are moving towards processing data in-situ, that is, on (or close to) the data generating devices. By learning models directly at the data sources - which often have computational power of their own, such as, mobile phones, smart sensors and tablets - network communication is reduced by orders of magnitude. Moreover, it facilitates obtaining a global model without centralizing privacy-sensitive data, thereby contributing to the development of trustworthy AI systems. This form of parallel, distributed, and federated machine learning has gained substantial interest in recent years, both from researchers and practitioners, and may allow for disruptive changes in areas such as smart assistants, machine learning on medical or industrial data, and autonomous driving. This workshop is the fourth edition of the successful PDFL (previously DMLE) workshops at ECMLPKDD 2018, 2019, and 2020. The workshop aims to foster discussion, discovery, and dissemination of novel ideas and approaches for parallel, distributed, federated and privacy-preserving machine learning.
We invite participation in the 3rd Workshop on Parallel, Distributed, and Federated Learning, to be held as part of the ECMLPKDD 2020 conference. This year we invite two types of submissions to the workshop:
- full length papers (16 pages)
- short papers (8 pages)
For all accepted papers, we invite the authors for a presentation as a poster. Moreover, for 4-6 papers, we invite the authors for a presentation as a talk during the workshop. We issue a Best Paper Award with certificate and a prize.
Topics
The main topics are, including, but not limited to:
- Federated learning
- Parallel machine learning
- On-device machine learning
- Edge computing for machine learning
- Decentralized deep learning
- In-situ methods
- Communication-efficient learning
- Privacy-preserving learning
- Black-box machine learning
- Distributed optimization
- Theoretical investigations on parallelization
- Large-scale machine learning, massive data sets
- Distributed data mining
- Fairness in Federated Learning
- Distributed Training of Generative Models
- Resource constraint machine learning
- Hardware aspects of distributed learning
Submission Guidelines
Authors should submit a PDF version in Springer LNCS style using the workshop's EasyChair site (https://easychair.org/conferences/?conf=pdfl21). The review process is single-blind. Papers will be published in the Springer LNCS ECMLPKDD workshop proceedings. Full papers have a page limit of 16 pages, short papers have 8 pages, including bibliography. Submitting a paper to the workshop means that if the paper is accepted at least one author commits to presenting it at the workshop. Papers not presented at the workshop will not be included in the proceedings.
Organizers
- Linara Adilova, Fraunhofer IAIS, Germany
- Michael Kamp, Monash University and CISPA, Germany
- Yamuna Krishnamurthy, Royal Holloway University of London, United Kingdom
Invited Speaker
Bharat Rao is a Partner / Principal in KPMG’s Advisory Services practice and leads KPMG’s health care and life sciences Data and Analytics (D\&A) practice. He has 25 years of experience using advanced analytics for clinical, financial, regulatory and operational improvement for health care and life sciences (HCLS) organizations. Bharat is a leading international expert in health analytics, big data, predictive modeling and personalized medicine. He is the recipient of multiple innovation awards, including the highest lifetime award in data analytics, and is a frequent speaker and a highly published author (100+ papers, 60+ granted patents, 1 book).
Blaise Agüera y Arcas leads an organization at Google AI working on both basic research and new products. Among the team’s public contributions are MobileNets, Federated Learning, Coral, and many Android and Pixel AI features. They also founded the Artists and Machine Intelligence program, and collaborate extensively with academic researchers in a variety of fields. Until 2014 Blaise was a Distinguished Engineer at Microsoft, where he worked in a variety of roles, from inventor to strategist, and led teams with strengths in interaction design, prototyping, machine vision, augmented reality, wearable computing and graphics. Blaise has given TED talks on Seadragon and Photosynth (2007, 2012), Bing Maps (2010), and machine creativity (2016). In 2008, he was awarded MIT’s TR35 prize.