# Embedded Federated Feature Selection with Dynamic Sparse Training: Balancing Accuracy-Cost Tradeoffs

arXiv: https://arxiv.org/abs/2504.05245 · HTML: https://mlsanity.com/paper/2504.05245/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Rigging the Lottery: Making All Tickets Winners](https://mlsanity.com/paper/1911.11134/) (2019)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science](https://mlsanity.com/paper/1707.04780/) (2017)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Cost-Effective Federated Learning Design](https://mlsanity.com/paper/2012.08336/) (2020)
- [Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better](https://mlsanity.com/paper/2112.09824/) (2021)
- [Dynamic Sparse Training for Deep Reinforcement Learning](https://mlsanity.com/paper/2106.04217/) (2021)
- [Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity](https://mlsanity.com/paper/2106.14568/) (2021)
- [Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders](https://mlsanity.com/paper/2012.00560/) (2020)
- [A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning](https://mlsanity.com/paper/2311.05877/) (2023)
- [Where to Pay Attention in Sparse Training for Feature Selection?](https://mlsanity.com/paper/2211.14627/) (2022)
- [FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning](https://mlsanity.com/paper/2302.10417/) (2023)
- [LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning](https://mlsanity.com/paper/2305.02219/) (2023)
- [Federated Feature Selection for Cyber-Physical Systems of Systems](https://mlsanity.com/paper/2109.11323/) (2021)
- [Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks](https://mlsanity.com/paper/2303.07200/) (2023)
- [Multimodal Multiple Federated Feature Construction Method for IoT Environments](https://mlsanity.com/paper/2308.07131/) (2023)

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

- [One Round Is All You Need: Analytic Federated Learning for Task-Heterogeneous Multi-Label Medical Image Classification](https://mlsanity.com/paper/2607.20641/) (2026)

## Abstract (arXiv)

Federated Learning (FL) enables multiple resource-constrained edge devices with varying levels of heterogeneity to collaboratively train a global model. However, devices with limited capacity can create bottlenecks and slow down model convergence. One effective approach to addressing this issue is to use an efficient feature selection method, which reduces overall resource demands by minimizing communication and computation costs, thereby mitigating the impact of struggling nodes. Existing federated feature selection (FFS) methods are either considered as a separate step from FL or rely on a third party. These approaches increase computation and communication overhead, making them impractical for real-world high-dimensional datasets. To address this, we present textitDynamic Sparse Federated Feature Selection (DSFFS), the first innovative embedded FFS that is efficient in both communication and computation. In the proposed method, feature selection occurs simultaneously with model training. During training, input-layer neurons, their connections, and hidden-layer connections are dynamically pruned and regrown, eliminating uninformative features. This process enhances computational efficiency on devices, improves network communication efficiency, and boosts global model performance. Several experiments are conducted on nine real-world datasets of varying dimensionality from diverse domains, including biology, image, speech, and text. The results under a realistic non-iid data distribution setting show that our approach achieves a better trade-off between accuracy, computation, and communication costs by selecting more informative features compared to other state-of-the-art FFS methods.