With the rapid development of AI-driven personalized services, model training increasingly depends on highly sensitive user-side data, such as location, social behaviour, and biometric information. These data not only exhibit pronounced non-independent and identically distributed (non-IID) characteristics but also pose serious privacy risks when processed centrally. Achieving efficient personalized modelling while preserving data locality and privacy has thus become a critical challenge in the evolution of personalized AI. In recent years, personalized federated learning (PFL) has gained significant attention for its strong performance in addressing non-IID data challenges. However, existing approaches often fall short in effectively balancing collaborative efficiency with personalization. To overcome this limitation, we propose FedDAC, a dynamically adaptive, collaboration-enhanced personalized federated learning method. By quantitatively assessing the responsiveness of each parameter to non-IID data, FedDAC dynamically selects collaborative clients, ensuring effective cooperation while retaining personalized feature information. Extensive experiments on four benchmark datasets (EMNIST, CIFAR-10, CIFAR-100, and Tiny ImageNet) under two pathological non-IID settings show that FedDAC consistently outperforms strong baselines. It improves accuracy by 1.5–3.2% on average, reaching 5.9% on highly heterogeneous tasks. The source code is publicly available at https://github.com/Lixinqin9/FedDAC-MAIN.
ChenH.-Y.ChaoW.-L. (2021). On bridging generic and personalized federated learning for image classification. arXiv preprint arXiv:2107.00778.
3.
ChenJ.-X.YanH.LiuZ.-Y.ZhangM.XiongH.YuS. (2024). When federated learning meets privacy-preserving computation. ACM Computing Surveys, ACM New York, NY.
4.
CohenG.AfsharS.TapsonJ.Van SchaikA. (2017). EMNIST: Extending MNIST to handwritten letters. In 2017 International joint conference on neural networks (IJCNN) (pp. 2921–2926). IEEE.
5.
CollinsL.HassaniH.MokhtariA.ShakkottaiS. (2021). Exploiting shared representations for personalized federated learning. In International conference on machine learning (pp. 2089–2099).
DinhC.TranN.NguyenJ. (2020). Personalized federated learning with moreau envelopes. Advances in Neural Information Processing Systems, 33, 21394–21405.
8.
FallahA.MokhtariA.OzdaglarA. (2020). Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. Advances in Neural Information Processing Systems, 33, 3557–3568.
9.
GhoshA.ChungJ.YinD.RamchandranK. (2020). An efficient framework for clustered federated learning. Advances in Neural Information Processing Systems, 33, 19586–19597.
10.
GongX.SharmaA.KaranamS.WuZ.ChenT.DoermannD.InnanjeA. (2021). Ensemble attention distillation for privacy-preserving federated learning. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 15076–15086).
11.
HimeurY.VarlamisI.KheddarH.AmiraA.AtallaS.SinghY.BensaaliF.MansoorW. (2023). Federated learning for computer vision. arXiv preprint arXiv:2308.13558.
12.
HuH.SalcicZ.SunL.DobbieG.ZhangX. (2021). Source inference attacks in federated learning. In 2021 IEEE international conference on data mining (ICDM) (pp. 1102–1107).
13.
HuangY.ChuL.ZhouZ.WangL.LiuJ.PeiJ.ZhangY. (2021). Personalized cross-silo federated learning on non-iid data. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, No. 9, pp. 7865–7873).
14.
KrizhevskyA.HintonG. (2009). Learning multiple layers of features from tiny images. In Toronto, ON, Canada.
LiQ.HeB.SongD. (2021). Model comparison federated learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10713–10722).
20.
LiT.HuS.BeiramiA.SmithV. (2021). Ditto: Fair and robust federated learning through personalization. In International conference on machine learning (pp. 6357–6368).
21.
LiT.SahuA. K.ZaheerM.SanjabiM.TalwalkarA.SmithV. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine Learning and Systems, 2, 429–450.
22.
LiW.WangC.ChengG.SongQ. (2023). Optimum-statistical collaboration towards general and efficient black-box optimization. arXiv preprint arXiv:2106.09215.
23.
LiX.JiangM.ZhangX.KampM.DouQ. (2021). Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623.
24.
LongG.TanY.JiangJ.ZhangC. (2020). Federated learning for open banking. In Federated Learning: Privacy and incentive (pp. 240–254). Springer.
25.
MarfoqO.NegliaG.BelletA.KameniL.VidalR. (2021). Federated multi-task learning under a mixture of distributions. Advances in Neural Information Processing Systems, 34, 15434–15447.
26.
McMahanB.MooreE.RamageD.HampsonS.ArcasB. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics (pp. 1273–1282).
27.
PeiJ.-M.LiuW.-X.LiJ.-H.WangL.-K.LiuC. (2024). A survey of federated learning methods in heterogeneous scenarios. IEEE Transactions on Consumer Electronics, 70(3), 5983–5999.
28.
RiekeN.HancoxJ.LiW.MilletarìF.RothH. R.AlbarqouniS.BakasS.GaltierM. N.LandmanB. A.Maier-HeinK. (2020). The future of digital health with federated learning. NPJ Digital Medicine, 3, 119.
29.
SadilekA.LiuL.NguyenD.KamruzzamanM.SerghiouS.RaderB.IngermanA.MellemS.KairouzP.NsoesieE. O. (2021). Privacy-first health research with federated learning. NPJ Digital Medicine, 4(1), 132.
30.
TanY.LongG.LiuL.ZhouT.LuQ.JiangJ.ZhangC. (2022). Fedproto: Federated prototype learning across heterogeneous clients. In Proceedings of the AAAI conference on artificial intelligence (Vol. 36, No. 8, pp. 8432–8440).
TaoJ.GaoZ.GuoZ. (2022). Training vision transformers in federated learning with limited edge-device resources. Electronics, 11(17), 2638.
33.
WangK.MathewsR.KiddonC.EichnerH.BeaufaysF.RamageD. (2019). Federated evaluation of on-device personalization. arXiv preprint arXiv:1910.10252.
34.
WuX.LiuX.NiuJ.ZhuG.TangS. (2023). Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collaboration. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 19375–19384).
35.
YoonT.ShinS.HwangS. J.YangE. (2021). Fedmix: Approximation of mixup under mean augmented federated learning. arXiv preprint arXiv:2107.00233.
36.
ZhangJ.HuaY.WangH.SongT.XueZ.MaR.GuanH. (2023). Fedala: Adaptive local aggregation for personalized federated learning. In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 9, pp. 11237–11244).
37.
ZhangL.LuoY.BaiY.DuB.DuanL.-Y. (2021). Federated learning for non-iid data via unified feature learning and optimization objective alignment. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 4420–4428).
38.
ZhangM.SapraK.FidlerS.YeungS.AlvarezJ. M. (2020). Personalized federated learning with first-order model optimization. arXiv preprint arXiv:2012.08565.
