Resource-Constrained Federated Learning with Heterogeneous Labels and Models

Gudur, Gautham Krishna; Balaji, Bala Shyamala; Perepu, Satheesh K.

doi:10.48550/arxiv.2011.03206

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reason for this is that users' personalized data is usually insufficient. The work in [74] identifies a new challenge in FL design, which is called label heterogeneity. Concretely, each FL device has its own definition of data labels and learning model, which is independent of the definitions in other devices and the central server.…”

Section: Personalized Flmentioning

confidence: 99%

See 1 more Smart Citation

Federated Learning for Smart Healthcare: A Survey

Nguyen¹,

Pham²,

Pathirana³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent advances in communication technologies and Internet-of-Medical-Things have transformed smart healthcare enabled by artificial intelligence (AI). Traditionally, AI techniques require centralized data collection and processing that may be infeasible in realistic healthcare scenarios due to the high scalability of modern healthcare networks and growing data privacy concerns. Federated Learning (FL), as an emerging distributed collaborative AI paradigm, is particularly attractive for smart healthcare, by coordinating multiple clients (e.g., hospitals) to perform AI training without sharing raw data. Accordingly, we provide a comprehensive survey on the use of FL in smart healthcare. First, we present the recent advances in FL, the motivations, and the requirements of using FL in smart healthcare. The recent FL designs for smart healthcare are then discussed, ranging from resource-aware FL, secure and privacy-aware FL to incentive FL and personalized FL. Subsequently, we provide a state-of-the-art review on the emerging applications of FL in key healthcare domains, including health data management, remote health monitoring, medical imaging, and COVID-19 detection. Several recent FL-based smart healthcare projects are analyzed, and the key lessons learned from the survey are also highlighted. Finally, we discuss interesting research challenges and possible directions for future FL research in smart healthcare.

show abstract

Section: Personalized Flmentioning

confidence: 99%

“…For example, the blood type is labeled as bloodtype in the device A; however, which is labeled as bltype in the device B. This new challenge is solved in [74] by devising an 𝛼-weighted update. Particularly, the overlapping information of labels of different devices is aggregated at the central server.…”

Section: Personalized Flmentioning

confidence: 99%

Federated Learning for Smart Healthcare: A Survey

Nguyen¹,

Pham²,

Pathirana³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Xie et al [11] presented a new approach called multi-center FL clustering, by constructing multiple global models and assigning them to the nearest local models. Many studies [17], [54], [55] have implemented auxiliary public dataset to minimize the biased distribution of class labels of existing clients, which accommodates the improvement of training performance in FL. Li et al [16] curated an additional public dataset that could assist the training among the local models and adopted transfer learning with knowledge distillation in the FL network.…”

Section: Related Workmentioning

confidence: 99%

“…These shortcomings imply that distance-based local weight clustering is an approach that is intractable to explain, which gives us an inspiration to design an algorithm that clusters through the given local labels. Although past several studies has emphasized that biased labels are major defect that perturbs the functionality under FL settings, they suggested alternatives [17], [54][55][56], [60], [61] such as implementing public dataset. To the best of our knowledge, there were no published articles that selects local models through evaluating their cor-responding labels with statistical metrics without using auxiliary dataset on FL framework.…”

Section: Related Workmentioning

confidence: 99%

Robust Convergence in Federated Learning through Label-wise Clustering

Lee¹,

Liu²,

Kim³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…(b) Local Update: In this step, if new classes are not reported, we perform simple weighted α-update [21], where α governs the contributions of new and old models across FL iterations shown in Algorithm 1 Choice 1. If new classes are reported, we train the new class data along with public dataset, and send the new model weights to global user (Choice 2).…”

Section: Proposed Frameworkmentioning

confidence: 99%

Zero-Shot Federated Learning with New Classes for Audio Classification

Gudur¹,

Perepu²

2021

Interspeech 2021

Self Cite

View full text Add to dashboard Cite

Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users. However, new classes with completely unseen data distributions can stream across any device in a federated learning setting, whose data cannot be accessed by the global server or other users. To this end, we propose a unified zero-shot framework to handle these aforementioned challenges during federated learning. We simulate two scenarios here -1) when the new class labels are not reported by the user, the traditional FL setting is used; 2) when new class labels are reported by the user, we synthesize Anonymized Data Impressions by calculating class similarity matrices corresponding to each device's new classes followed by unsupervised clustering to distinguish between new classes across different users. Moreover, our proposed framework can also handle statistical heterogeneities in both labels and models across the participating users. We empirically evaluate our framework on-device across different communication rounds (FL iterations) with new classes in both local and global updates, along with heterogeneous labels and models, on two widely used audio classification applications -keyword spotting and urban sound classification, and observe an average deterministic accuracy increase of ∼4.041% and ∼4.258% respectively.

show abstract

Resource-Constrained Federated Learning with Heterogeneous Labels and Models

Cited by 3 publications

References 0 publications

Federated Learning for Smart Healthcare: A Survey

Federated Learning for Smart Healthcare: A Survey

Robust Convergence in Federated Learning through Label-wise Clustering

Zero-Shot Federated Learning with New Classes for Audio Classification

Contact Info

Product

Resources

About