Track 1

With the rapid proliferation of Internet of Things (IoT) devices and the growing demand for real-time intelligent services, edge intelligence has emerged as a key paradigm for next-generation AI systems. This track focuses on novel theories, algorithms, and systems for collaborative intelligence across edge, cloud, and end devices. It emphasizes distributed learning, multi-agent coordination, and resource-efficient AI under heterogeneous and dynamic environments. Topics include federated and decentralized learning, edge-cloud collaboration, on-device intelligence, and communication-efficient training. This track also encourages interdisciplinary research bridging machine learning, networking, and systems design, with applications in smart cities, autonomous systems, intelligent manufacturing, and beyond. By integrating learning, communication, and computation, this track aims to advance scalable, privacy-preserving, and adaptive intelligent systems for real-world deployment.

The topics of interest include, but are not limited to:

1. Federated Learning and Personalized Federated Optimization
2. Decentralized and Distributed Machine Learning
3. Edge-Cloud Collaborative Intelligence
4. Communication-Efficient Learning and Model Compression
5. Heterogeneity-Aware Learning (Data, Model, System Heterogeneity)
6. Continual and Lifelong Learning at the Edge
7. Resource-Aware AI (Computation, Energy, and Latency Optimization)
8. AI for Networked Systems and Edge Computing
9. Privacy-Preserving and Secure Collaborative Learning
10. On-Device Intelligence and TinyML
11. Task Offloading and Intelligent Scheduling in Edge Environments
12. Edge AI Applications in Smart Cities, IoT, and Autonomous Systems

Submission Guidelines

Please submit your manuscript via Electronic Submission System (account is needed). (Please choose the special number when you make the submission.)

Important Dates

    ◆ Submission of Full Papers: May. 15, 2026
    ◆ Notification of Review Result of Papers from Tracks: May. 30, 2026