# When Foresight Pruning Meets Zeroth-Order Optimization: Efficient Federated Learning for Low-Memory Devices

arXiv: https://arxiv.org/abs/2405.04765 · HTML: https://mlsanity.com/paper/2405.04765/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 8 May 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges](https://mlsanity.com/paper/2009.13012/) (2020)
- [Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning](https://mlsanity.com/paper/2111.14213/) (2021)
- [Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things](https://mlsanity.com/paper/2011.08612/) (2020)
- [Fast Sparse ConvNets](https://mlsanity.com/paper/1911.09723/) (2019)
- [On Generalization Error Bounds of Noisy Gradient Methods for Non-Convex Learning](https://mlsanity.com/paper/1902.00621/) (2019)
- [Federated Dynamic Sparse Training: Computing Less, Communicating Less, Yet Learning Better](https://mlsanity.com/paper/2112.09824/) (2021)
- [ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity](https://mlsanity.com/paper/2208.02507/) (2022)
- [Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts](https://mlsanity.com/paper/2305.18691/) (2023)
- [Convergence Analysis of Sequential Federated Learning on Heterogeneous Data](https://mlsanity.com/paper/2311.03154/) (2023)
- [Zeroth-Order Algorithms for Stochastic Distributed Nonconvex Optimization](https://mlsanity.com/paper/2106.02958/) (2021)
- [BAFFLE: A Baseline of Backpropagation-Free Federated Learning](https://mlsanity.com/paper/2301.12195/) (2023)
- [Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach](https://mlsanity.com/paper/2302.05726/) (2023)
- [HADFL: Heterogeneity-aware Decentralized Federated Learning Framework](https://mlsanity.com/paper/2111.08274/) (2021)

## Built on by (most cited first, 2 of 2)

- [Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization](https://mlsanity.com/paper/2602.17155/) (2026)
- [Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale](https://mlsanity.com/paper/2501.19099/) (2025)

## Abstract (arXiv)

Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated pruning methods are proposed to reduce memory usage during inference. However, few of them can substantially mitigate the memory burdens during pruning and training. As an alternative, zeroth-order or backpropagation-free (BP-Free) methods can partially alleviate the memory consumption, but they suffer from scaling up and large computation overheads, since the gradient estimation error and floating point operations (FLOPs) increase as the dimensionality of the model parameters grows. In this paper, we propose a federated foresight pruning method based on Neural Tangent Kernel (NTK), which can seamlessly integrate with federated BP-Free training frameworks. We present an approximation to the computation of federated NTK by using the local NTK matrices. Moreover, we demonstrate that the data-free property of our method can substantially reduce the approximation error in extreme data heterogeneity scenarios. Since our approach improves the performance of the vanilla BP-Free method with fewer FLOPs and truly alleviates memory pressure during training and inference, it makes FL more friendly to low-memory devices. Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.