# Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning

arXiv: https://arxiv.org/abs/2512.12737 · HTML: https://mlsanity.com/paper/2512.12737/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 14 Dec 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [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)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://mlsanity.com/paper/1705.09056/) (2017)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization](https://mlsanity.com/paper/1905.13727/) (2019)
- [Decentralized Federated Averaging](https://mlsanity.com/paper/2104.11375/) (2021)
- [Decentralized Federated Learning: A Survey and Perspective](https://mlsanity.com/paper/2306.01603/) (2023)
- [DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training](https://mlsanity.com/paper/2206.00187/) (2022)
- [Improving the Model Consistency of Decentralized Federated Learning](https://mlsanity.com/paper/2302.04083/) (2023)
- [Momentum Benefits Non-IID Federated Learning Simply and Provably](https://mlsanity.com/paper/2306.16504/) (2023)
- [A Survey on Decentralized Federated Learning](https://mlsanity.com/paper/2308.04604/) (2023)
- [TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels](https://mlsanity.com/paper/2207.06343/) (2022)
- [Neural Tangent Kernel Empowered Federated Learning](https://mlsanity.com/paper/2110.03681/) (2021)
- [Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning](https://mlsanity.com/paper/2306.00127/) (2023)
- [Dynamic Heterogeneous Federated Learning with Multi-Level Prototypes](https://mlsanity.com/paper/2312.09881/) (2023)
- [NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel](https://mlsanity.com/paper/2410.01922/) (2024)
- [Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning](https://mlsanity.com/paper/2509.22082/) (2025)

## Abstract (arXiv)

Decentralized federated learning (DFL) enables collaborative model training without a central server, but converges slowly under statistical heterogeneity. Recent work has shown that neural tangent kernel (NTK) methods achieve faster convergence than gradient-based updates in DFL, while momentum has proven effective for accelerating gradient-based FL. However, applying momentum to NTK updates can destabilize training under heterogeneous data. We propose SPARK, which addresses this instability with a stage-wise annealed soft-label regularizer evaluated on neighborhood-aggregated data, so that momentum can accelerate NTK updates stably. Under high heterogeneity, SPARK converges about 3× faster than baselines and lowers the total communication to a target accuracy by up to about 70%, and it attains higher accuracy across heterogeneity levels. We further study random projection as an optional Jacobian-compression strategy for bandwidth-constrained settings. We validate the approach across multiple datasets, network topologies, and heterogeneity levels.