Optimization Stability in Federated Learning under Non-IID Data: A Comparative Study of FedAvg and FedProx with Deep Convolutional Neural Network Architectures

Federated Learning with SVMs: Dynamic SGD for Efficient Hyperparameter Optimization

In the current digital landscape, organizations are actively looking for user data to make informed decisions at the edge. This raises a need for a solution that prioritizes user privacy while leveraging user's data. Federated learning (FL) emerges as a viable solution to address this issue. However, these methods are dominated by complex, resource-intensive neural networks (NN). This necessitates the development of an FL technique that protects user privacy while employing lightweight models. Support vector machines (SVMs) provide a lightweight alternative, but their traditional training techniques, such as quadratic programming and sequential minimal optimization, are inefficient and incompatible with FL. Existing stochastic gradient descent (SGD)-based SVM variants also depend on fixed or heuristic learning rates, which restrict convergence under non-IID data and client heterogeneity. In this paper, we propose a novel meta-learned dynamic learning rate controller for SGD-trained SVMs in federated settings. Unlike standard adaptive optimizers, the controller adapts learning rates over each epoch and clients. This process enables faster convergence and lower communication overhead to heterogeneous data. Empirical evaluations on benchmark datasets show that federated SVM framework provides effective results comparable to NN-based FL approaches while significantly less computational and communication overhead. Received: 29 September 2025 | Revised: 30 March 2026 | Accepted: 9 July 2026Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Kaggle at https://git-disl.github.io/GTDLBench/datasets/mnist_datasets/ (MNIST), the NIST repository at https://www.nist.gov/itl/products-and-services/emnist-dataset (FEMNIST), and the University of Toronto's repository at https://www.cs.toronto.edu/~kriz/cifar.html (CIFAR-10). Author Contribution Statement Deebakkarthi Chinnasame Rani: Methodology, Software, Validation, Formal analysis, Investigation, Resources, Writing – original draft, Writing – review & editing. Gowtham Ramesh: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Writing – original draft, Writing – review & editing, Supervision, Project administration. Sountharrajan Sehar: Validation, Formal analysis, Investigation, Resources, Data curation, Writing – review & editing, Project administration. Varun Aiyaswamy Kannan: Formal analysis, Resources, Data curation. Elambharathi Padmavathi Thangavel: Formal analysis, Writing – original draft, Visualization. Bharath Kumar Kanapareddy: Investigation, Resources, Data curation.

Towards Neuro-Symbolic Federated Tree Learning

Federated Learning (FL) is a distributed machine learning paradigm that enables multiple clients to collaboratively train a model while keeping their data localized, thus preserving privacy. While most FL approaches focus on deep learning models, there is a growing interest in exploring alternative models that can offer interpretability and efficiency. This paper presents TreeClimber, a novel neuro-symbolic approach for training decision tree models in a federated setting using gradient-free optimization techniques. TreeClimber embeds data into a subsymbolic latent space via a randomized embedding, from which decision trees are reconstructed through a neural architecture. Trees are optimized in the embedding space in a federated setting using a zeroth-order approximation of the gradient, allowing for effective training of interpretable decision models without direct access to data. Experimental results demonstrate the effectiveness of TreeClimber in enabling secure distributed training of decision trees without sharing raw information about local datasets, achieving competitive performance compared to traditional centralized training methods.

FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life Estimation

Data-driven prognostics and health management has emerged as a key enabler for Industry 4.0, yet the development of robust remaining useful life (RUL) estimation models is often limited by the scarcity of run-to-failure data. While federated learning offers a promising paradigm to collaboratively train predictive models without sharing sensor data, research efforts have operated so far in the absence of a common evaluation framework. To address this gap, this paper introduces FedCMAPSS, a benchmark for federated RUL estimation based on the commonly-used NASA C-MAPSS dataset. We define a set of five standardized tasks designed to simulate real-world industrial challenges, ranging from ideal IID settings to extreme statistical heterogeneity, and conduct a systematic evaluation of state-of-the-art federated optimization algorithms across multiple neural architectures. By establishing reproducible baselines and making the source code and data splits publicly available, this work aims to provide a standard foundation for developing and comparing federated predictive maintenance solutions.

Empowering Non-IID Federated Learning With Data Augmentation and Data-Free Knowledge Distillation

Federated learning (FL) is an emerging distributed machine learning framework that enables collaborative learning among multiple parties while preserving data privacy. However, the complexity of environments and node heterogeneity in the real world result in uneven data distribution across nodes, leading to Non-IID (Non-Independent and Identically Distributed) characteristics in data distribution. Such data distribution significantly reduces the convergence and performance of the model, becoming one of the fundamental challenges in federated learning mechanisms. To address the above issue, this paper proposes a novel FL framework-FedGKD. For the Non-IID client data distribution problem, we employ client-side local data augmentation, where GAN models are deployed on each client to generate synthetic samples so that local data distribution imbalance can be effectively alleviated. To further overcome the limitations of client-side local data augmentation under Non-IID, FedGKD introduces server-side privacy-preserving data-free knowledge distillation, which can transfer the knowledge of selected clients to the server while ensuring privacy protection, further mitigating the impact of Non-IID on federated learning and solving the problem of model performance degradation caused by direct aggregation. Extensive experiments demonstrate that FedGKD significantly outperforms the baseline algorithms in terms of accuracy, while exhibiting excellent performance in other metrics.

Federated learning for medical image classification based on prototype alignment

FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging

This work proposes a prototype-based, influence-aware federated learning framework (FedProIn) that uses multiple learnable class prototypes to capture shared semantic structures across heterogeneous clients and introduces feature divergence loss and prototype contrastive loss to mitigate client drift by decomposing it into feature drift and prototype drift.