RIFLES: Resource-effIcient Federated LEarning via Scheduling
Sara Alosaime, Arshad Jhumka
TL;DR
RIFLES tackles the inefficiency of myopic client selection in Federated Learning by introducing an availability forecasting layer that leverages heartbeat signals to predict long-horizon client participation. It formalizes the scheduling problem, proves NP-hardness, and pairs a CNN-LSTM-based availability predictor with two adaptive policies (GH and LRU) to improve client selection and timing across rounds. Experimental results on HAR (WISDM) and CIFAR-10 demonstrate 10-50% gains in accuracy, faster convergence, and better resource efficiency compared with baselines like Random, FedCS, and REFL, validating the practical value of scheduling-aware FL. The framework’s server-side middleware enables smarter participation decisions, reduces dropouts, and mitigates wasteful communication, offering scalable improvements for heterogeneous and availability-variable FL deployments.
Abstract
Federated Learning (FL) is a privacy-preserving machine learning technique that allows decentralized collaborative model training across a set of distributed clients, by avoiding raw data exchange. A fundamental component of FL is the selection of a subset of clients in each round for model training by a central server. Current selection strategies are myopic in nature in that they are based on past or current interactions, often leading to inefficiency issues such as straggling clients. In this paper, we address this serious shortcoming by proposing the RIFLES approach that builds a novel availability forecasting layer to support the client selection process. We make the following contributions: (i) we formalise the sequential selection problem and reduce it to a scheduling problem and show that the problem is NP-complete, (ii) leveraging heartbeat messages from clients, RIFLES build an availability prediction layer to support (long term) selection decisions, (iii) we propose a novel adaptive selection strategy to support efficient learning and resource usage. To circumvent the inherent exponential complexity, we present RIFLES, a heuristic that leverages clients' historical availability data by using a CNN-LSTM time series forecasting model, allowing the server to predict the optimal participation times of clients, thereby enabling informed selection decisions. By comparing against other FL techniques, we show that RIFLES provide significant improvement by between 10%-50% on a variety of metrics such as accuracy and test loss. To the best of our knowledge, it is the first work to investigate FL as a scheduling problem.