# GCA: Global Centroid Alignment in Federated Learning

arXiv: https://arxiv.org/abs/2608.22593 · HTML: https://mlsanity.com/paper/2608.22593/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 45 references that are in the map.
- First posted on arXiv 23 Aug 2026.

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

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition](https://mlsanity.com/paper/1608.04636/) (2016)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [Recent Advances in Autoencoder-Based Representation Learning](https://mlsanity.com/paper/1812.05069/) (2018)
- [Detailed comparison of communication efficiency of split learning and federated learning](https://mlsanity.com/paper/1909.09145/) (2019)
- [End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things](https://mlsanity.com/paper/2003.13376/) (2020)
- [Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation](https://mlsanity.com/paper/2102.10365/) (2021)
- [Communication-Efficient Federated Distillation](https://mlsanity.com/paper/2012.00632/) (2020)
- [Splitting methods with variable metric for KL functions](https://mlsanity.com/paper/1405.1357/) (2014)
- [Generative Latent Coding for Ultra-Low Bitrate Image Compression](https://mlsanity.com/paper/2512.20194/) (2025)
- [Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search](https://mlsanity.com/paper/1803.00370/) (2018)
- [Fast Deep Autoencoder for Federated learning](https://mlsanity.com/paper/2206.05136/) (2022)
- [SelfFed: Self-Supervised Federated Learning for Data Heterogeneity and Label Scarcity in Medical Images](https://mlsanity.com/paper/2307.01514/) (2023)
- [Statistical Inference for Autoencoder-based Anomaly Detection after Representation Learning-based Domain Adaptation](https://mlsanity.com/paper/2508.07049/) (2025)

## Abstract (arXiv)

Autoencoder (AE)-based federated learning (FL) is attractive for anomaly detection when clients have limited local data. However, conventional FL exchanges AE parameters or gradients, incurring substantial communication overhead and potentially exposing input training data information, since AEs are explicitly optimized to reconstruct their inputs. We introduce Global Centroid Alignment (GCA), a latent-code-mediated FL protocol that coordinates clients without transmitting AE parameters or gradients. In each round, (1) clients first train their local AEs using a reconstruction update and upload a small subset of encoder latent codes to the FL server. (2) The server pools these codes, fits a clustering model, and broadcasts only global latent centroids and their support counts. (3) Each client then updates its encoder by aligning its local latent codes with the nearest centroid using inverse-count weighting to emphasize globally underrepresented patterns. Steps (1)--(3) repeat over communication rounds. Because GCA exchanges only sampled latent codes and centroid statistics, its communication cost depends on latent dimensionality and the numbers of uploaded codes and returned centroids rather than on AE model size. Across five tabular and two vision benchmarks, GCA yields higher reconstruction error under a server-side client data extraction attack in all 21 comparisons and clearly lower cosine similarity in 20 of 21 comparisons with FedAvg, FedProx, and FedNova, showing its ability to protect training data. It even improves test accuracy over FedAvg by up to 5.76%. GCA achieves extraction defense comparable to DP-FedAvg, remains effective when DP-FedAvg does not reduce target resemblance, and lowers per-round communication by up to 99.15%.