Towards efficient communications in federated learning: A contemporary survey

Zhao, Zihao; Mao, Yuzhu; Liu, Yang; Song, Linqi; Ouyang, Ye; Chen, Xinlei; Ding, Wenbo

doi:10.1016/j.jfranklin.2022.12.053

Cited by 18 publications

(9 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to that taxonomy, the setup considered here is horizontal FL. Zhao et al, 2023, discuss FL from the communication efficiency point of view. An overview of FL applications can be found in C. There are also surveys that are specific to certain fields; (Pandya et al, 2023) discuss FL methods and challenges in the context of smart cities, while 1 4th Asia Pacific Conference of the Prognostics and Health Management, Tokyo, Japan, September 11 -14, 2023 R03-07 (Nguyen et al, 2021;Khan et al, 2021) provide a taxonomy of FL for IoT services and applications.…”

Section: Related Workmentioning

confidence: 99%

Analysis of Statistical Data Heterogeneity in Federated Fault Identification

Taghiyarrenani,

Nowaczyk,

Pashami

2023

PHMAP_CONF

View full text Add to dashboard Cite

Federated Learning (FL) is a setting where different clients collaboratively train a Machine Learning model in a privacy-preserving manner, i.e., without the requirement to share data. Given the importance of security and privacy in real-world applications, FL is gaining popularity in many areas, including predictive maintenance. For example, it allows independent companies to construct a model collaboratively. However, since different companies operate in different environments, their working conditions may differ, resulting in heterogeneity among their data distributions. This paper considers the fault identification problem and simulates different scenarios of data heterogeneity. Such a setting remains challenging for popular FL algorithms, and thus we demonstrate the considerations to be taken into account when designing federated predictive maintenance solutions.

show abstract

Section: Related Workmentioning

confidence: 99%

Analysis of Statistical Data Heterogeneity in Federated Fault Identification

Taghiyarrenani,

Nowaczyk,

Pashami

2023

PHMAP_CONF

View full text Add to dashboard Cite

show abstract

“…Federated Learning (FL) has been proposed by Google to enable distributed Machine Learning (ML) model execution [1]. According to this paradigm, distributed clients (typically mobile devices), coordinated by an aggregator server, collaboratively train a shared ML model by using their own private data.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the well-known advantages, FL faces communication challenges. In particular, some clients may experience connectivity issues due to unreliable and lossy links, thus becoming communication stragglers that deteriorate the FL convergence [1]. To mitigate such effect, a variety of client selection mechanisms have been proposed that exclude stragglers from training [2].…”

Section: Introductionmentioning

confidence: 99%

Mitigating the Communication Straggler Effect in Federated Learning via Named Data Networking

Amadeo,

Campolo,

Molinaro

et al. 2024

IEEE Commun. Mag.

View full text Add to dashboard Cite

Federated learning (FL) has emerged as a prominent solution that enables distributed training of machine learning (ML) models at multiple end-devices with their own data samples. The FL performance, and in particular, the training convergence speed, are limited by the device with the lowest computation and communication capabilities typically referred to as a straggler. In this work, we address the issues related to the presence of communication stragglers, that is, devices experiencing poor channel conditions. By leveraging named data networking (NDN) and customizing its forwarding fabric to improve the ML model delivery in the presence of lossy communications, our solution allows potential stragglers to beneficially participate in the FL application. Results show the advantages of the conceived solution in terms of reduced training time when compared to a conventional host-centric FL approach, and higher accuracy with reference to the case in which stragglers are not selected.

show abstract

“…Recently, FL has confronted a wealth of challenges, including significant communication overheads [19,26,27] and data heterogeneity [13]. A variety of recent research initiatives have sought to tackle these obstacles.…”

Section: Introductionmentioning

confidence: 99%

Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt

Zhao,

Shi,

Liu

et al. 2023

Adjunct Proceedings of the 2023 ACM International Joint Conference on Pervasive and Ubiquitous Computing &Amp; The 2023 ACM Int

View full text Add to dashboard Cite

Federated Learning (FL) is often impeded by communication overhead issues. Prompt tuning, as a potential solution, has been introduced to only adjust a few trainable parameters rather than the whole model. However, current single-modality prompt tuning approaches fail to comprehensively portray local clients' data. To overcome this limitation, we present Twin Prompt Federated learning (TPFL), a pioneering solution that integrates both visual and textual modalities, ensuring a more holistic representation of local clients' data characteristics. Furthermore, in order to tackle the data heterogeneity issues, we introduce the Augmented TPFL (ATPFL) employing the contrastive learning to TPFL, which not only enhances the global knowledge acquisition of client models but also fosters the development of robust, compact models. The effectiveness of TPFL and ATPFL is substantiated by our extensive evaluations, consistently showing superior performance compared to all baselines. CCS CONCEPTS• Human-centered computing → Empirical studies in ubiquitous and mobile computing; Collaborative and social computing;• Computing methodologies → Distributed algorithms.

show abstract

Towards efficient communications in federated learning: A contemporary survey

Cited by 18 publications

References 65 publications

Analysis of Statistical Data Heterogeneity in Federated Fault Identification

Analysis of Statistical Data Heterogeneity in Federated Fault Identification

Mitigating the Communication Straggler Effect in Federated Learning via Named Data Networking

Inclusive Data Representation in Federated Learning: A Novel Approach Integrating Textual and Visual Prompt

Contact Info

Product

Resources

About