# Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

arXiv: https://arxiv.org/abs/2607.08013 · HTML: https://mlsanity.com/paper/2607.08013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data](https://mlsanity.com/paper/1811.11479/) (2018)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [Expanding the Reach of Federated Learning by Reducing Client Resource Requirements](https://mlsanity.com/paper/1812.07210/) (2018)
- [Attribute Prototype Network for Zero-Shot Learning](https://mlsanity.com/paper/2008.08290/) (2020)
- [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://mlsanity.com/paper/1804.03230/) (2018)
- [Federated Evaluation of On-device Personalization](https://mlsanity.com/paper/1910.10252/) (2019)
- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation](https://mlsanity.com/paper/1812.08934/) (2018)
- [SqueezeNext: Hardware-Aware Neural Network Design](https://mlsanity.com/paper/1803.10615/) (2018)
- [Predicting the Computational Cost of Deep Learning Models](https://mlsanity.com/paper/1811.11880/) (2018)
- [Do We Need More Training Data?](https://mlsanity.com/paper/1503.01508/) (2015)
- [High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors](https://mlsanity.com/paper/1903.05898/) (2019)

## Built on by (most cited first, 1 of 1)

- [On Hardware-Aware Design and Optimization of Edge Intelligence](https://mlsanity.com/paper/2607.16297/) (2026)

## Abstract (arXiv)

Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a severe impact on the performance of the inferred model. Existing optimizations on FL focus on improving the training efficiency but fail to speed up inference, especially when there is a latency constraint. In this work, we propose Collate, a novel training framework that collaboratively learns heterogeneous models to meet the latency constraints of multiple edge systems simultaneously. We design a dynamic zeroizing-recovering method to adjust each local model architecture for high accuracy under its latency constraint. A proto-corrected federated aggregation scheme is also introduced to aggregate all heterogeneous local models, satisfying the latency constraint of different systems with only one training process and maintaining high accuracy. Extensive experiments indicate that, compared to state-of-the-art methods and under a latency constraint, our extended models can improve the accuracy by 1.96% on average, and our shrunk models can also obtain a 3.09% accuracy improvement on average, with almost no extra training overhead. The related codes and data will be available at https://github.com/ntuliuteam/Collate