Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings

2026-04-12 · Cristiano Mafuz, Rodrigo Silva arxiv

Federated learning (FL) performance is highly sensitive to heterogeneity across clients, yet practitioners lack reliable methods to anticipate how a federation will behave before training. We propose readiness indices, derived from Task2Vec embeddings, that quantifies the alignment of a federation prior to training and correlates with its eventual performance. Our approach computes unsupervised metrics -- such as cohesion, dispersion, and density -- directly from client embeddings. We evaluate these indices across diverse datasets (CIFAR-10, FEMNIST, PathMNIST, BloodMNIST) and client counts (10--20), under Dirichlet heterogeneity levels spanning $α\in \{0.05,\dots,5.0\}$ and FedAVG aggregation strategy. Correlation analyses show consistent and significant Pearson and Spearman coefficients between some of the Task2Vec-based readiness and final performance, with values often exceeding 0.9 across dataset$\times$client configurations, validating this approach as a robust proxy for FL outcomes. These findings establish Task2Vec-based readiness as a principled, pre-training diagnostic for FL that may offer both predictive insight and actionable guidance for client selection in heterogeneous federations.

📄 PDF Abstract BibTeX arXiv:2604.10849

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective

2026-05-09 · Jiuqi Wang, Jayanth Srinivasa, Claire Chen, Shuze Daniel Liu 외 arxiv

Deep continual learning requires models to adapt to new tasks without retraining from scratch. However, neural networks can lose their ability to adapt to new tasks after training on previous ones, a phenomenon known as …

Continual Learning

AIDRIN 2.0: A Framework to Assess Data Readiness for AI

2025-05-22 · Kaveen Hiniduma, Dylan Ryan, Suren Byna, Jean Luca Bez 외

AI Data Readiness Inspector (AIDRIN) is a framework to evaluate and improve data preparedness for AI applications. It addresses critical data readiness dimensions such as data quality, bias, fairness, and privacy. This p…

Fairness Federated Learning Privacy Preserving

CADRE: Customizable Assurance of Data Readiness in Privacy-Preserving Federated Learning

2025-05-28 · Kaveen Hiniduma, Zilinghan Li, Aditya Sinha, Ravi Madduri 외

Privacy-Preserving Federated Learning (PPFL) is a decentralized machine learning approach where multiple clients train a model collaboratively. PPFL preserves privacy and security of the client's data by not exchanging i…

Fairness Federated Learning Privacy Preserving

Cross-device Federated Learning for Mobile Health Diagnostics: A First Study on COVID-19 Detection

2023-03-13 · Tong Xia, Jing Han, Abhirup Ghosh, Cecilia Mascolo

Federated learning (FL) aided health diagnostic models can incorporate data from a large number of personal edge devices (e.g., mobile phones) while keeping the data local to the originating devices, largely ensuring pri…

Diagnostic Federated Learning Privacy Preserving

A Survey on Efficient Federated Learning Methods for Foundation Model Training

2024-01-09 · Herbert Woisetschläger, Alexander Isenko, Shiqiang Wang, Ruben Mayer 외

Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. However, new approaches to FL often discuss their contributions involving…

Federated Learning parameter-efficient fine-tuning Privacy Preserving