FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources

Md Sirajul Islam; Isabelle G Chapman; N I Md Ashafuddula; Xu Yuan; Li Chen; Nian-Feng Tzeng; Klara Nahrstedt

cs.LGMar 11, 2026

FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources

Authors: Md Sirajul Islam, Isabelle G Chapman, N I Md Ashafuddula, Xu Yuan, Li Chen, Nian-Feng Tzeng, Klara Nahrstedt

Organizations: School of Computing and Informatics, University of Louisiana at Lafayette, USA · Department of Computer and Information Sciences, University of Delaware, USA · Department of Computer Science, University of Illinois at Urbana-Champaign, USA

Abstract

Federated Learning (FL) enables collaborative intelligence across decentralized data source devices in a privacy-preserving way. While substantial research attention has been drawn to optimizing the learning process for an individual task, real-world applications increasingly require multiple machine learning tasks simultaneously training their models across a shared pool of devices. Naively applying single-FL optimization techniques in multi-FL systems results in suboptimal system performance, particularly due to device heterogeneity and resource inefficiency. To address such a critical open challenge, we introduce {\em FedACT}, a novel resource heterogeneity-aware device scheduling approach designed to efficiently schedule heterogeneous devices across multiple concurrent FL jobs, with the goal of minimizing their average job completion time (JCT). {\em FedACT} dynamically assigns devices to FL jobs based on an alignment scoring mechanism that evaluates the compatibility between available resources of devices and resource demands of jobs. Additionally, it incorporates participation fairness to ensure balanced contributions from devices across jobs, further enhancing the accuracy levels of learned global models. An optimal scheduling plan is formulated in {\em FedACT} by prioritizing devices with higher alignment scores, while ensuring fair participation across jobs. To evaluate the effectiveness of the proposed scheduling algorithm, we carried out comprehensive experiments using diverse FL jobs and benchmark datasets. Experimental results demonstrate that {\em FedACT} reduces the average JCT by up to 8.3 $\times$ and improves model accuracy by up to 44.5%, compared to the state-of-the-art baselines.

Figures & tables

Fig. 1 : An example of Multi-Job Federated Learning: smartphones simultaneously improve next-word prediction for keyboards while enhancing image quality.

Notation	Definition
$\mathcal{K}$ ; $\|\mathcal{K}\|$	Set of all devices; the total number of devices
$M$ ; $T$ ; $m$	The total number of jobs; total training time; job index
$D_{k}^{m}$ ; $d_{k}^{m}$ ; $\|D_{k}^{m}\|$	The local dataset on Device $k$ for Job $m$ ; batch size; size of $D_{k}^{m}$
$D^{m}$ ; $\|D^{m}\|$	Global dataset of Job $m$ ; size of $D^{m}$
$F_{k}^{m}(\boldsymbol{w})$ ; $F^{m}(\boldsymbol{w})$	Local loss function of Device $k$ for Job $m$ ; global loss function of Job $m$
$\boldsymbol{w}_{k}^{m,r}(j)$	Local model of Job $m$ in Device $k$ in the $j$ -th local update of Round $r$

TABLE I : Notations and Descriptions

Fig. 2 : An overview of the training procedure within the FedACT framework.

	Group A			Group B
Datasets	Cifar-10	Emnist (L)	Emnist (D)	Fashion-Mnist	Cifar-10	Mnist
Features	32 $\times$ 32	28 $\times$ 28	28 $\times$ 28	28 $\times$ 28	32 $\times$ 32	28 $\times$ 28
Model Architecture	VGG-16	CNN	LeNet-5	CNN	ResNet-18	AlexNet
Model Parameters	26,233K	3,785K	62K	225K	598k	3,275K
Dataset Size	50k/10k	124.8k/20.8k	240k/40k	60K/10K	50K/10K	60K/10K
Local epochs	5	5	5	5	5	5

TABLE II : A summary of the datasets and models used in our experiments. The dataset size indicates the number of training samples and test samples (number of training samples/number of test samples). Emnist (L) and Emnist (D) represent Emnist-Letters and Emnist-Digits, respectively.

	Convergence Accuracy						Time (min)
	Random	Greedy	Genetic	MJ-FL	FedACT		Random	Greedy	Genetic	MJFL	FedACT
	IID
LeNet	0.9924	0.990	0.9931	0.9937	0.9943	LeNet(0.99)	15.13	17.25	6.42	5.18	3.92
CNN	0.942	0.926	0.928	0.935	0.942	CNN(0.93)	58.41	30.17	109.68	19.18	11.52
VGG	0.611	0.52	0.557	0.602	0.605	VGG(0.55)	134.3	/	229.7	59.10	43.25
	Non-IID

TABLE III : Elapsed wall-clock time needed to reach the convergence accuracy and target accuracy (shown in parentheses) for different methods in Group A. “/” denotes that the method failed to achieve the target accuracy.

	Convergence Accuracy						Time (min)
	Random	Greedy	Genetic	MJ-FL	FedACT		Random	Greedy	Genetic	MJFL	FedACT
	IID
AlexNet	0.9937	0.9834	0.9938	0.9939	0.9942	AlexNet(0.9933)	37.02	/	20.28	21.90	13.58
CNN	0.868	0.868	0.867	0.868	0.871	CNN(0.867)	123.10	36.88	40.08	31.35	21.08
ResNet	0.786	0.742	0.753	0.784	0.796	ResNet(0.74)	64.66	52.68	31.26	16.65	11.42
	Non-IID

TABLE IV : Elapsed wall-clock time needed to reach the convergence accuracy and target accuracy (shown in parentheses) for different methods in Group B. “/” denotes that the method failed to achieve the target accuracy.

Job	VGG	CNN	LeNet	ResNet	CNN	AlexNet
	IID/Non-IID			IID/Non-IID
Target Accuracy	0.55/0.55	0.93/0.80	0.99/0.984	0.74/0.50	0.867/0.73	0.9933/0.976
Time (min)	140.7/2488.3	49.6/52.4	19.1/49.5	*/896.7	32.1/36.8	67.02/116.5

TABLE V : Elapsed wall-clock time needed to reach the target accuracy in Single-Job FL using FedAvg. “*” denotes that it fails to reach the target accuracy.

Panel of Figure 8 — Fig. 3 : Test accuracy versus elapsed wall-clock time for different jobs in Group A with the IID distribution.

Panel of Figure 9 — Fig. 4 : Test accuracy versus elapsed wall-clock time for different jobs in Group B with the IID distribution.

Panel of Figure 10 — Fig. 5 : Test accuracy versus elapsed wall-clock time for different jobs in Group A with the Non-IID distribution.

Panel of Figure 11 — Fig. 6 : Test accuracy versus elapsed wall-clock time for different jobs in Group B with the Non-IID distribution.

Panel of Figure 12 — Fig. 7 : Elapsed wall-clock training time required for each job of Group A to achieve the target convergence accuracy under IID and Non-IID data distributions.

Panel of Figure 13 — Fig. 8 : Elapsed wall-clock training time required for each job of Group B to achieve the target convergence accuracy under IID and Non-IID data distributions.

Online Federated Learning

See all 9 papers

FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment
Jun 1, 2026Nazmus Shakib Shadin, Aaron Cummings, Xinyue Zhang +1Non-IID Federated Learning Multi-Teacher Knowledge Distillation
Department of Computer Science, Kennesaw State University, Marietta, GA, 30060 USA
Adaptive Determinantal Client Scheduling in Federated Learning
Sep 20, 2026Wen Xu, Ben Liang, Gary Boudreau +1Client Selection in Federated Learning Federated Learning
University of Toronto, Canada · Ericsson, Canada
Latent Information Sharing for Accelerating Federated Learning
Oct 1, 2026Seungjun Lee, Ensieh Khazaei, Dimitrios Hatzinakos +2Federated Learning Aggregation Federated Learning
Inha University · University of Toronto · University of Birmingham

Jun 1, 2026J/K move · Enter open · S save

FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment

Nazmus Shakib Shadin, Aaron Cummings, Xinyue Zhang, Bobin Deng

Department of Computer Science, Kennesaw State University, Marietta, GA, 30060 USA

Non-IID Federated Learning Multi-Teacher Knowledge Distillation Clustered Federated Learning Heterogeneous Federated Learning

Open paper AskPDF arXiv

Federated learning (FL) is a decentralized approach that enables collaborative model training without exposing raw data. Instead of transferring sensitive data, it allows devices to share only model weights, keeping personal data locally and secure. However, in real world settings, the data held by devices is often not evenly distributed and devices mostly differ in computing power and memory capacity. These differences make FL harder to maintain consistent performance across the system. To address these issues, we propose FedMTFI, a novel architecture that combines multi-teacher knowledge distillation (MTKD) with feature importance to improve the FL process in heterogeneous environments. In FedMTFI, clients are clustered based on similar hardware and model types. Each cluster trains a specific model on not independently and identically distributed (non-IID) data. Within a cluster, every client updates that model using only its own local private data. The server then aggregates the locally trained models in each cluster using FedAvg to form multiple prototype models. Then these prototypes serve as teacher models to train a global generalized student model using MTKD. What makes FedMTFI more unique is the integration of Shapley values (SHAP) to emphasize important features during distillation, which enhances both accuracy and interpretability. Experimental results show that FedMTFI achieves higher accuracy than traditional FL algorithms and performs more effectively under non-IID data conditions.

Abstract

Online Federated Learning

Explore similar work

FedMTFI: Feature Importance Based Optimized Multi Teacher Knowledge Distillation in Heterogeneous Federated Learning Environment

Adaptive Determinantal Client Scheduling in Federated Learning

Latent Information Sharing for Accelerating Federated Learning