# CorrFL: Correlation-Based Neural Network Architecture for Unavailability Concerns in a Heterogeneous IoT Environment

arXiv: https://arxiv.org/abs/2307.12149 · HTML: https://mlsanity.com/paper/2307.12149/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 47 references that are in the map.
- First posted on arXiv 22 Jul 2023.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Insights on representational similarity in neural networks with canonical correlation](https://mlsanity.com/paper/1806.05759/) (2018)
- [Convergent Learning: Do different neural networks learn the same representations?](https://mlsanity.com/paper/1511.07543/) (2015)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [Generalized Shape Metrics on Neural Representations](https://mlsanity.com/paper/2110.14739/) (2021)
- [Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer](https://mlsanity.com/paper/1912.11279/) (2019)
- [Energy Demand Prediction with Federated Learning for Electric Vehicle Networks](https://mlsanity.com/paper/1909.00907/) (2019)
- [Correlational Neural Networks](https://mlsanity.com/paper/1504.07225/) (2015)
- [Internet of Things: An Overview](https://mlsanity.com/paper/1703.06409/) (2017)
- [FedREP: Towards Horizontal Federated Load Forecasting for Retail Energy Providers](https://mlsanity.com/paper/2203.00219/) (2022)
- [Federated Learning with Hyperparameter-based Clustering for Electrical Load Forecasting](https://mlsanity.com/paper/2111.07462/) (2021)
- [ModularFed: Leveraging Modularity in Federated Learning Frameworks](https://mlsanity.com/paper/2212.10427/) (2022)
- [Sound Event Classification in an Industrial Environment: Pipe Leakage Detection Use Case](https://mlsanity.com/paper/2205.02706/) (2022)

## Built on by (most cited first, 3 of 3)

- [On TinyML and Cybersecurity: Electric Vehicle Charging Infrastructure Use Case](https://mlsanity.com/paper/2404.16894/) (2024)
- [Efficient Transformer-based Hyper-parameter Optimization for Resource-constrained IoT Environments](https://mlsanity.com/paper/2403.12237/) (2024)
- [Thwarting Cybersecurity Attacks with Explainable Concept Drift](https://mlsanity.com/paper/2403.13023/) (2024)

## Abstract (arXiv)

The Federated Learning (FL) paradigm faces several challenges that limit its application in real-world environments. These challenges include the local models' architecture heterogeneity and the unavailability of distributed Internet of Things (IoT) nodes due to connectivity problems. These factors posit the question of "how can the available models fill the training gap of the unavailable models?". This question is referred to as the "Oblique Federated Learning" problem. This problem is encountered in the studied environment that includes distributed IoT nodes responsible for predicting CO2 concentrations. This paper proposes the Correlation-based FL (CorrFL) approach influenced by the representational learning field to address this problem. CorrFL projects the various model weights to a common latent space to address the model heterogeneity. Its loss function minimizes the reconstruction loss when models are absent and maximizes the correlation between the generated models. The latter factor is critical because of the intersection of the feature spaces of the IoT devices. CorrFL is evaluated on a realistic use case, involving the unavailability of one IoT device and heightened activity levels that reflect occupancy. The generated CorrFL models for the unavailable IoT device from the available ones trained on the new environment are compared against models trained on different use cases, referred to as the benchmark model. The evaluation criteria combine the mean absolute error (MAE) of predictions and the impact of the amount of exchanged data on the prediction performance improvement. Through a comprehensive experimental procedure, the CorrFL model outperformed the benchmark model in every criterion.