# Multi Part Deployment of Neural Network

arXiv: https://arxiv.org/abs/2506.01387 · HTML: https://mlsanity.com/paper/2506.01387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [LLM-based Multi-Agent Systems: Techniques and Business Perspectives](https://mlsanity.com/paper/2411.14033/) (2024)
- [Partitioning and Deployment of Deep Neural Networks on Edge Clusters](https://mlsanity.com/paper/2304.11941/) (2023)
- [Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables](https://mlsanity.com/paper/2409.07485/) (2024)
- [Modular and Integrated AI Control Framework across Fiber and Wireless Networks for 6G](https://mlsanity.com/paper/2502.15731/) (2025)
- [A Deep Neural Network Deployment Based on Resistive Memory Accelerator Simulation](https://mlsanity.com/paper/2304.11337/) (2023)
- [Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones](https://mlsanity.com/paper/2402.15273/) (2024)

## Abstract (arXiv)

The increasing scale of modern neural networks, exemplified by architectures from IBM (530 billion neurons) and Google (500 billion parameters), presents significant challenges in terms of computational cost and infrastructure requirements. As deep neural networks continue to grow, traditional training paradigms relying on monolithic GPU clusters become increasingly unsustainable. This paper proposes a distributed system architecture that partitions a neural network across multiple servers, each responsible for a subset of neurons. Neurons are classified as local or remote, with inter-server connections managed via a metadata-driven lookup mechanism. A Multi-Part Neural Network Execution Engine facilitates seamless execution and training across distributed partitions by dynamically resolving and invoking remote neurons using stored metadata. All servers share a unified model through a network file system (NFS), ensuring consistency during parallel updates. A Neuron Distributor module enables flexible partitioning strategies based on neuron count, percentage, identifiers, or network layers. This architecture enables cost-effective, scalable deployment of deep learning models on cloud infrastructure, reducing dependency on high-performance centralized compute resources.