1. Workshop Scope & Motivation

As cloud, edge, and mobile computing continue to converge into a unified computing ecosystem, there is a growing opportunity for edge platforms to support computationally intensive AI models as services similar to the cloud AI services. However, constraints on scheduling, distribution, and resource managements making large scale adoption slow. Considering these challenges \textbf{Scheduling and Parallelism for AI in Distributed Edge } (SPADE) aims to collect novel contributions on the architecture, algorithmic, and practical challenges of deploying computationally intensive applications (Deep learning, Generative AI, LLM, etc) across distributed edge computing. While edge AI offers low-latency and privacy-preserving inference for IoT, the inability to efficiently parallelize tasks often limits system performance. This workshop targets the combination of computationally intensive models handling parallelism limits, AI computation and scheduling optimization with resource-constrained, and heterogeneous edge networks. SPADE will bring together researchers and practitioners working on model partitioning, decentralized scheduling, execution frameworks, hybrid AI pipelines, and benchmarking testbeds. In addition, it will address bottlenecks in distributed inference and highlight new strategies for intelligent scheduling and task coordination. The contributions on model slicing, distributed inference, workload orchestration, task-to-node mapping, and scalable deployment of AI for IoT systems through presentations, discussion sessions, and short papers is welcome.

2. Topics of Interest

We will consider submissions on a wide range of topics in these domains including (but not limited to):

• Task distribution and scheduling for computationally intensive models on edge devices
• Parallelism-aware model design for edge AI and TinyML
• Resource-aware AI deployment strategies
• Hybrid edge-cloud execution frameworks
• Model partitioning and distributed inference
• Federated and decentralized scheduling approaches
• Real-time and latency-sensitive computing at the edge
• Benchmarking and testbeds for edge-based AI
• Energy-efficient task coordination in IoT systems
• Middleware and OS-level support for distributed edge AI
• Applications in industrial IoT, surveillance, transportation, health, and smart cities
• Compiler support and hardware-aware optimizations for edge AI models
• Scheduling algorithms for constrained and heterogeneous environments
• Containerization and orchestration tools (e.g., Docker, Kubernetes) for edge deployments
• Cross-layer design strategies for scheduling and data placement
• Adaptive and real-time load balancing across edge nodes and TinyML
• Distributed training and continual learning at the edge
• Privacy-preserving computation and secure model execution
• Communication-efficient algorithms for collaborative edge inference
• Use of reinforcement learning for task offloading and scheduling

Submission Guidelines

Submissions to SPADE 2025 must be in PDF format and use the official ACM conference style templates for MS Word and LaTeX. We welcome two types of submissions:

• Short papers (Work-in-progress): up to 3 pages (excluding references)

• Full papers: up to 6 pages (excluding references)

Special Issue

Extended versions of selected papers will be invited for publication in the Special Issue:

Contemporary Mathematics for Changing Computational DemandsSCI | IF (2024): 2.5 | Deadline: 01 July 2026A 30% APC discount will be offered for SPADE 2025 contributors.

Committees

Program Committee

• Dr. Dinesh Kumar Sah
• Dr. Praveen Kumar Donta
• Dr. Lauri Lovén
• Dr. Priyanka Verma

Organizing committee

• TBA

Technical Program Committee (TPC) Members

Venue

The conference/workshop will be held along with the The 15th International Conference on the Internet of Things (IoT 2025)  by end of November 2025 in Vienna, Austria.

IoT 2025 will be organised in a fully physical format by TU Wien

Contact

For inquiries, please contact: dinesh.sah@oulu.fi