InterDigital and The University of Texas at Austin to Showcase Over-the-Air Federated Learning for AI Model Training at Brooklyn 6G Summit
InterDigital and The University of Texas at Austin will showcase Over-the-Air Federated Learning (OTA-FL) for AI model training at the 2024 Brooklyn 6G Summit. The demo addresses challenges in applying AI/ML to wireless networks by managing model training overhead and ensuring user data privacy. OTA-FL allows simultaneous transmission of model updates, reducing overhead and improving energy efficiency compared to traditional federated learning.
The live demo will use software defined radios (SDRs) to display real-time OTA-FL training for image classification. InterDigital's Senior Principal Engineer Phil Pietraski will also participate in a panel discussion on 'Energy Efficiency in AI/ML Networks' during the summit, which focuses on the theme '6G – From vision to action'.
InterDigital e l'Università del Texas ad Austin presenteranno l'Apprendimento Federato Over-the-Air (OTA-FL) per l'addestramento dei modelli AI al 2024 Brooklyn 6G Summit. La demo affronta le sfide nell'applicazione di AI/ML alle reti wireless gestendo il sovraccarico dell'addestramento dei modelli e garantendo la privacy dei dati degli utenti. L'OTA-FL consente la trasmissione simultanea degli aggiornamenti del modello, riducendo il sovraccarico e migliorando l'efficienza energetica rispetto all'apprendimento federato tradizionale.
La demo dal vivo utilizzerà radio definite dal software (SDR) per mostrare l'addestramento in tempo reale dell'OTA-FL per la classificazione delle immagini. Phil Pietraski, Senior Principal Engineer di InterDigital, parteciperà anche a una discussione di panel su 'Efficienza Energetica nelle Reti AI/ML' durante il summit, che si concentra sul tema '6G – Dalla visione all'azione'.
InterDigital y la Universidad de Texas en Austin presentarán Aprendizaje Federado Over-the-Air (OTA-FL) para el entrenamiento de modelos de IA en la Cumbre 6G de Brooklyn 2024. La demostración aborda los desafíos en la aplicación de IA/ML a redes inalámbricas al gestionar la sobrecarga de entrenamiento de modelos y asegurar la privacidad de los datos de los usuarios. OTA-FL permite la transmisión simultánea de actualizaciones de modelos, reduciendo la sobrecarga y mejorando la eficiencia energética en comparación con el aprendizaje federado tradicional.
La demostración en vivo utilizará radios definidas por software (SDR) para mostrar el entrenamiento OTA-FL en tiempo real para la clasificación de imágenes. Phil Pietraski, ingeniero principal de InterDigital, también participará en un panel de discusión sobre 'Eficiencia Energética en Redes de IA/ML' durante la cumbre, que se centra en el tema '6G – De la visión a la acción'.
InterDigital과 텍사스 대학교 오스틴 캠퍼스는 2024 브루클린 6G 서밋에서 AI 모델 훈련을 위한 오버 더 에어 연합 학습 (OTA-FL)을 선보일 예정입니다. 이번 데모는 모델 훈련 오버헤드를 관리하고 사용자 데이터 프라이버시를 보장함으로써 무선 네트워크에 AI/ML을 적용하는 데 있어 발생하는 문제를 다룹니다. OTA-FL은 모델 업데이트의 동시 전송을 허용하여 전통적인 연합 학습에 비해 오버헤드를 줄이고 에너지 효율성을 개선합니다.
이번 라이브 데모는 소프트웨어 정의 라디오 (SDR)를 사용하여 이미지 분류를 위한 실시간 OTA-FL 훈련을 보여줄 것입니다. InterDigital의 수석 수석 엔지니어인 Phil Pietraski는 서밋 동안 'AI/ML 네트워크에서의 에너지 효율성'에 대한 패널 토론에도 참여할 예정이며, 서밋의 주제는 '6G – 비전에서 행동으로'입니다.
InterDigital et l'Université du Texas à Austin présenteront l'Apprentissage Fédéré Over-the-Air (OTA-FL) pour la formation de modèles d'IA lors du Sommet 6G de Brooklyn 2024. La démonstration aborde les défis de l'application de l'IA/ML aux réseaux sans fil en gérant la surcharge de formation des modèles et en garantissant la confidentialité des données des utilisateurs. L'OTA-FL permet la transmission simultanée des mises à jour des modèles, réduisant la surcharge et améliorant l'efficacité énergétique par rapport à l'apprentissage fédéré traditionnel.
La démonstration en direct utilisera des radios définies par logiciel (SDR) pour afficher la formation OTA-FL en temps réel pour la classification des images. Phil Pietraski, ingénieur principal chez InterDigital, participera également à un débat sur 'Efficacité Énergétique dans les Réseaux IA/ML' lors du sommet, qui se concentre sur le thème '6G – De la vision à l'action'.
InterDigital und die Universität Texas in Austin werden das Over-the-Air Federated Learning (OTA-FL) für das Training von KI-Modellen auf dem 2024 Brooklyn 6G Summit vorstellen. Die Demo thematisiert Herausforderungen bei der Anwendung von KI/ML auf drahtlose Netzwerke, indem sie die Trainingsüberheads der Modelle verwaltet und die Privatsphäre der Nutzerdaten gewährleistet. OTA-FL ermöglicht die gleichzeitige Übertragung von Modellaktualisierungen, wodurch der Overhead reduziert und die Energieeffizienz im Vergleich zum traditionellen föderierten Lernen verbessert wird.
Die Live-Demo wird Software-definierte Radios (SDRs) verwenden, um das OTA-FL-Training in Echtzeit zur Bilderkennung zu demonstrieren. Phil Pietraski, Senior Principal Engineer bei InterDigital, wird auch an einer Podiumsdiskussion über 'Energieeffizienz in KI/ML-Netzwerken' während des Gipfels teilnehmen, der sich dem Thema '6G – Von der Vision zur Aktion' widmet.
- Collaboration with The University of Texas at Austin on cutting-edge AI technology for wireless networks
- Showcase of innovative Over-the-Air Federated Learning (OTA-FL) technology at a major industry event
- OTA-FL reduces overhead and improves energy efficiency in AI model training
- None.
WILMINGTON, Del., Oct. 21, 2024 (GLOBE NEWSWIRE) -- InterDigital, Inc. (Nasdaq: IDCC), a mobile, video and AI technology research and development company, announced its participation in the 2024 Brooklyn 6G Summit, taking place October 23 – 25. At the show, InterDigital and researchers from The University of Texas at Austin will display the latest in their collaboration to validate AI solutions for wireless networks and shape how AI will be used for 5G and 6G.
Jointly organized by Nokia and the NYU Wireless Research Center, the Brooklyn Summit is an annual gathering of communications industry leaders contributing to the future of wireless technology. The theme of this year’s discussions is “6G – From vision to action.”
A key challenge in applying AI/ML to wireless networks is managing model training overhead and ensuring user data privacy. To address these issues, InterDigital and The University of Texas at Austin will showcase our research on Over-the-Air Federated Learning (OTA-FL) by training a real-time image classification in a live demo.
While traditional federated learning (FL) requires each device to send its model updates using separate dedicated radio resources to a central server for aggregation, in OTA-FL, the aggregation of model updates happens directly "over-the-air". The joint demo between InterDigital and The University of Texas at Austin will use software defined radios (SDRs) to simultaneously transmit model updates, displaying real-time OTA-FL training. The simultaneous transmission of model updates reduces overhead and improves energy efficiency, especially as the number of users increases.
“As industry prepares for the increased use of AI, new solutions are required to enable AI – especially for the training of AI models,” said Milind Kulkarni, VP and Head of Wireless Labs at InterDigital. “Our expert teams at InterDigital are leading critical research in AI and its enablement in wireless networks, and this work is one example of the novel approaches being considered”
“OTA-FL offers an incredible opportunity to have model weight updates from large number of devices without proportional increase in precious spectrum and time resources. It is a whole new paradigm of training where the wireless medium computes for us,” said UT-Austin Professor Kaushik Chowdhury. “Through this collaboration and support from InterDigital, as well as from the US National Science Foundation, we are excited to be among the first demonstrators of OTA-FL on real-world experimental testbeds.”
In addition to their AI demo showcase, InterDigital’s Senior Principal Engineer Phil Pietraski will participate in a panel discussion on “Energy Efficiency in AI/ML Networks,” alongside speakers from NVIDIA, Fraunhofer Heinrich Hertz Institute (HHI), Rohde & Schwarz, and MediaTek. The panel will take place on Friday, October 25th at 1:40pm ET in the NYU Wireless Pfizer Auditorium. Learn more here.
Learn more about the Brooklyn 6G Summit here.
About InterDigital®
InterDigital is a global research and development company focused primarily on wireless, video, artificial intelligence (“AI”), and related technologies. We design and develop foundational technologies that enable connected, immersive experiences in a broad range of communications and entertainment products and services. We license our innovations worldwide to companies providing such products and services, including makers of wireless communications devices, consumer electronics, IoT devices, cars and other motor vehicles, and providers of cloud-based services such as video streaming. As a leader in wireless technology, our engineers have designed and developed a wide range of innovations that are used in wireless products and networks, from the earliest digital cellular systems to 5G and today’s most advanced Wi-Fi technologies. We are also a leader in video processing and video encoding/decoding technology, with a significant AI research effort that intersects with both wireless and video technologies. Founded in 1972, InterDigital is listed on Nasdaq.
InterDigital is a registered trademark of InterDigital, Inc.
For more information, visit: www.interdigital.com.
InterDigital Contact:
Roya Stephens
Email: Roya.Stephens@interdigital.com
+1 (202) 349-1714
FAQ
What will InterDigital (IDCC) showcase at the 2024 Brooklyn 6G Summit?
How does OTA-FL improve upon traditional federated learning for InterDigital (IDCC)?
What panel will InterDigital (IDCC) participate in at the 2024 Brooklyn 6G Summit?
What is the theme of the 2024 Brooklyn 6G Summit where InterDigital (IDCC) is participating?
