Search Results for author: Schahram Dustdar

Found 20 papers, 8 papers with code

Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning

1 code implementation9 Oct 2024 Anastasiya Danilenka, Alireza Furutanpey, Victor Casamayor Pujol, Boris Sedlak, Anna Lackinger, Maria Ganzha, Marcin Paprzycki, Schahram Dustdar

Specifically, we introduce a conceptual agent for heterogeneous pervasive systems that permits setting global systems constraints as high-level SLOs.

Federated Learning

Adaptive Stream Processing on Edge Devices through Active Inference

no code implementations26 Sep 2024 Boris Sedlak, Victor Casamayor Pujol, Andrea Morichetta, Praveen Kumar Donta, Schahram Dustdar

The current scenario of IoT is witnessing a constant increase on the volume of data, which is generated in constant stream, calling for novel architectural and logical solutions for processing it.

Autonomous Driving

Distributed AI in Zero-touch Provisioning for Edge Networks: Challenges and Research Directions

no code implementations29 Nov 2023 Abhishek Hazra, Andrea Morichetta, Ilir Murturi, Lauri Lovén, Chinmaya Kumar Dehury, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

Zero-touch network is anticipated to inaugurate the generation of intelligent and highly flexible resource provisioning strategies where multiple service providers collaboratively offer computation and storage resources.

CommunityAI: Towards Community-based Federated Learning

no code implementations29 Nov 2023 Ilir Murturi, Praveen Kumar Donta, Schahram Dustdar

Federated Learning (FL) has emerged as a promising paradigm to train machine learning models collaboratively while preserving data privacy.

Federated Learning

Equilibrium in the Computing Continuum through Active Inference

no code implementations28 Nov 2023 Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

We present our framework for collaborative edge intelligence enabling individual edge devices to (1) develop a causal understanding of how to enforce their SLOs, and (2) transfer knowledge to speed up the onboarding of heterogeneous devices.

Designing Reconfigurable Intelligent Systems with Markov Blankets

no code implementations17 Nov 2023 Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

Compute Continuum (CC) systems comprise a vast number of devices distributed over computational tiers.

Active Inference on the Edge: A Design Study

no code implementations17 Nov 2023 Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

Machine Learning (ML) is a common tool to interpret and predict the behavior of distributed computing systems, e. g., to optimize the task distribution between devices.

Distributed Computing

Federated Domain Generalization: A Survey

no code implementations2 Jun 2023 Ying Li, Xingwei Wang, Rongfei Zeng, Praveen Kumar Donta, Ilir Murturi, Min Huang, Schahram Dustdar

FDG combines the strengths of federated learning (FL) and domain generalization (DG) techniques to enable multiple source domains to collaboratively learn a model capable of directly generalizing to unseen domains while preserving data privacy.

Domain Generalization Federated Learning +1

Architectural Vision for Quantum Computing in the Edge-Cloud Continuum

1 code implementation9 May 2023 Alireza Furutanpey, Johanna Barzen, Marvin Bechtold, Schahram Dustdar, Frank Leymann, Philipp Raith, Felix Truger

We discuss the necessity, challenges, and solution approaches for extending existing work on classical edge computing to integrate QPUs.

Collaborative Inference Edge-computing +2

FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing

1 code implementation21 Feb 2023 Alireza Furutanpey, Philipp Raith, Schahram Dustdar

The rise of mobile AI accelerators allows latency-sensitive applications to execute lightweight Deep Neural Networks (DNNs) on the client side.

Data Compression Edge-computing +4

Intelligent Computing: The Latest Advances, Challenges and Future

no code implementations21 Nov 2022 Shiqiang Zhu, Ting Yu, Tao Xu, Hongyang Chen, Schahram Dustdar, Sylvain Gigan, Deniz Gunduz, Ekram Hossain, Yaochu Jin, Feng Lin, Bo Liu, Zhiguo Wan, Ji Zhang, Zhifeng Zhao, Wentao Zhu, Zuoning Chen, Tariq Durrani, Huaimin Wang, Jiangxing Wu, Tongyi Zhang, Yunhe Pan

In recent years, we have witnessed the emergence of intelligent computing, a new computing paradigm that is reshaping traditional computing and promoting digital revolution in the era of big data, artificial intelligence and internet-of-things with new computing theories, architectures, methods, systems, and applications.

Survey

Multi-Component Optimization and Efficient Deployment of Neural-Networks on Resource-Constrained IoT Hardware

1 code implementation20 Apr 2022 Bharath Sudharsan, Dineshkumar Sundaram, Pankesh Patel, John G. Breslin, Muhammad Intizar Ali, Schahram Dustdar, Albert Zomaya, Rajiv Ranjan

The majority of IoT devices like smartwatches, smart plugs, HVAC controllers, etc., are powered by hardware with a constrained specification (low memory, clock speed and processor) which is insufficient to accommodate and execute large, high-quality models.

Anomaly Detection Model Optimization

Roadmap for Edge AI: A Dagstuhl Perspective

no code implementations27 Nov 2021 Aaron Yi Ding, Ella Peltonen, Tobias Meuser, Atakan Aral, Christian Becker, Schahram Dustdar, Thomas Hiessl, Dieter Kranzlmuller, Madhusanka Liyanage, Setareh Magshudi, Nitinder Mohan, Joerg Ott, Jan S. Rellermeyer, Stefan Schulte, Henning Schulzrinne, Gurkan Solmaz, Sasu Tarkoma, Blesson Varghese, Lars Wolf

Based on the collective input of Dagstuhl Seminar (21342), this paper presents a comprehensive discussion on AI methods and capabilities in the context of edge computing, referred as Edge AI.

Edge-computing

Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting

3 code implementations ICLR 2022 Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X. Liu, Schahram Dustdar

Accurate prediction of the future given the past based on time series data is of paramount importance, since it opens the door for decision making and risk management ahead of time.

Decision Making Management +2

Cannot find the paper you are looking for? You can Submit a new open access paper.