Federated Learning from Big Data Over Networks

SarcheshmehPour, Yasmin; Leinonen, Matti; Jung, Alexander

doi:10.1109/icassp39728.2021.9414903

Cited by 9 publications

(4 citation statements)

References 16 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the loss and regularizer function for ridge regression in (10), the action-value function can be expressed as…”

Section: Procedures At Client Kmentioning

confidence: 99%

“…Several challenges associated with the practical implementation of FL, such as communication efficiency [4], privacy preservation [5], byzantine attacks [6], and asynchronous behavior of devices and communication links [7], have been studied extensively in the literature. In contrast to single-server methodologies, multiserver architectures [8], [9] and fully distributed architectures [10] have also been studied recently. This paper deals with a fully distributed architecture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Networked Personalized Federated Learning Using Reinforcement Learning

Gauthier,

Gogineni,

Werner

2023

ICC 2023 - IEEE International Conference on Communications

View full text Add to dashboard Cite

Personalized federated learning enables every edge device or group of edge devices within the distributed network to learn a device-or cluster-specific model tailored to their local needs. Data scarcity, however, makes it difficult to learn such individual models, resulting in performance degradation. Since the device-or cluster-specific tasks are distinct but often related, leveraging these similarities through inter-cluster learning alleviates data shortage and enhances learning performance. Although inter-cluster learning can boost performance, uncontrolled intercluster learning may lead to performance degradation due to over-or under-usage of local similarity enforcement. In light of this issue, an intelligent mechanism that performs inter-cluster learning based on device-specific needs is required. To this end, this paper proposes adopting reinforcement learning principles to control device-specific inter-cluster learning in real-time. We propose networked personalized federated learning using reinforcement learning (NPFed-RL) as a general framework and then demonstrate its feasibility by applying it to the ridge regression problem. We conduct numerical experiments to compare the proposed method with the state-of-the-art. The proposed method successfully controls device-specific parameters and offers better learning performance than existing solutions.

show abstract

“…the loss and regularizer function for ridge regression in (10), the action-value function can be expressed as…”

Section: Procedures At Client Kmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Networked Personalized Federated Learning Using Reinforcement Learning

Gauthier,

Gogineni,

Werner

2023

ICC 2023 - IEEE International Conference on Communications

View full text Add to dashboard Cite

show abstract

“…Two specific choices are φ(v) := v 2 , which is used by nLasso [25], and φ(v) := (1/2) v 2 2 which is used by "MOCHA" [54]. Another recent FL method for networked data uses the choice φ(v) := v 1 [50].…”

Section: Generalized Total Variation Minimizationmentioning

confidence: 99%

“…The FL algorithm MOCHA [54] is obtained from (4) for the choice φ(v) := v 2 2 . Another special case of (4), obtained for the choice φ(v) := v 1 , has been studied recently [50].…”

Section: Generalized Total Variation Minimizationmentioning

confidence: 99%

Networked Federated Learning

SarcheshmehPour¹,

Tian²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many important application domains generate distributed collections of heterogeneous local datasets. These local datasets are often related via an intrinsic network structure that arises from domain-specific notions of similarity between local datasets. Different notions of similarity are induced by spatio-temporal proximity, statistical dependencies or functional relations. We use this network structure to adaptively pool similar local datasets into nearly homogenous training sets for learning tailored models. Our main conceptual contribution is to formulate networked federated learning using the concept of generalized total variation (GTV) minimization as a regularizer. This formulation is highly flexible and can be combined with almost any parametric model including Lasso or deep neural networks. We unify and considerably extend some well-known approaches to federated multi-task learning. Our main algorithmic contribution is a novel federated learning algorithm which is well suited for distributed computing environments such as edge computing over wireless networks. This algorithm is robust against model misspecification and numerical errors arising from limited computational resources including processing time or wireless channel bandwidth. As our main technical contribution, we offer precise conditions on the local models as well on their network structure such that our algorithm learns nearly optimal local models. Our analysis reveals an interesting interplay between the (information-) geometry of local models and the (cluster-) geometry of their network.Preprint. Under review.

show abstract

Financing Issues of Small and Micro Enterprises from the Perspective of the Linkage of Government, Finance and Enterprise in the Big Data Network

He¹

2022

2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)

View full text Add to dashboard Cite

Federated Learning from Big Data Over Networks

Cited by 9 publications

References 16 publications

Networked Personalized Federated Learning Using Reinforcement Learning

Networked Personalized Federated Learning Using Reinforcement Learning

Networked Federated Learning

Financing Issues of Small and Micro Enterprises from the Perspective of the Linkage of Government, Finance and Enterprise in the Big Data Network

Contact Info

Product

Resources

About