A Heterogeneous Federated Transfer Learning Approach with Extreme Aggregation and Speed

Abstract

Federated learning (FL) is a data-privacy-preserving, decentralized process that allows local edge devices of smart infrastructures to train a collaborative model independently while keeping data localized. FL algorithms, encompassing a well-structured average of the training parameters (e.g., the weights and biases resulting from training-based stochastic gradient descent variants), are subject to many challenges, namely expensive communication, systems heterogeneity, statistical heterogeneity, and privacy concerns. In this context, our paper targets the four aforementioned challenges while focusing on reducing communication and computational costs by involving recursive least squares (RLS) training rules. Accordingly, to the best of our knowledge, this is the first time that the RLS algorithm is modified to completely accommodate non-independent and identically distributed data (non-IID) for federated transfer learning (FTL). Furthermore, this paper also introduces a newly generated dataset capable of emulating such real conditions and of making data investigation available on ordinary commercial computers with quad-core microprocessors and less need for higher computing hardware. Applications of FTL-RLS on the generated data under different levels of complexity closely related to different levels of cardinality lead to a variety of conclusions supporting its performance for future uses.

Prognosease: A Data Generator for Health Deterioration Prognosis

“…𝑆𝑆 𝑆𝑆𝐸𝐸 = 𝑆𝑆 𝑁𝑁 * * + 𝜌𝜌 (10) Figure 3 is an example constructing a sensor measurements according to a sinusoidal with exponential growth trend with 𝑃𝑃(𝑥𝑥) is a Gaussian noise, 𝜗𝜗 = 0.1, 𝑛𝑛𝜌𝜌 = 2, 𝑤𝑤 = 0.1. 𝛼𝛼 𝑆𝑆𝐸𝐸 = 0.02, and 𝜔𝜔 = 0.2. (11) while (12) is describing the final output signal.…”

“…• PrognosEase also allows experiments to be done according decentralized and federated learning [12].…”

Federated Learning for Condition Monitoring of Industrial Processes: A Review on Fault Diagnosis Methods, Challenges, and Prospects

“…Reducing the complexity of learning algorithms: Focusing on studying simpler effective architectures, such as in [60], is necessary to overcome expansive communication issues.…”