D3FL: Data Distribution and Detrending for Robust Federated Learning in Non-linear Time-series Data

TL;DR

This paper explores how data distribution and detrending techniques impact federated learning accuracy on non-linear, non-stationary time-series data from IoT devices, proposing methods to improve model robustness.

Contribution

It introduces an analysis of non-linear data distributions and detrending methods in federated learning for time-series forecasting, highlighting their effects on performance.

Findings

Federated learning underperforms compared to centralized models on non-linear data.

Proper detrending techniques enhance federated learning accuracy.

Data distribution significantly influences federated learning effectiveness.

Abstract

With advancements in computing and communication technologies, the Internet of Things (IoT) has seen significant growth. IoT devices typically collect data from various sensors, such as temperature, humidity, and energy meters. Much of this data is temporal in nature. Traditionally, data from IoT devices is centralized for analysis, but this approach introduces delays and increased communication costs. Federated learning (FL) has emerged as an effective alternative, allowing for model training across distributed devices without the need to centralize data. In many applications, such as smart home energy and environmental monitoring, the data collected by IoT devices across different locations can exhibit significant variation in trends and seasonal patterns. Accurately forecasting such non-stationary, non-linear time-series data is crucial for applications like energy consumption estimation and weather forecasting. However, these data variations can severely impact prediction accuracy. The key contributions of this paper are: (1) Investigating how non-linear, non-stationary time-series data distributions, like generalized extreme value (gen-extreme) and log norm distributions, affect FL performance. (2) Analyzing how different detrending techniques for non-linear time-series data influence the forecasting model's performance in a FL setup. We generated several synthetic time-series datasets using non-linear data distributions and trained an LSTM-based forecasting model using both centralized and FL approaches. Additionally, we evaluated the impact of detrending on real-world datasets with non-linear time-series data distributions. Our experimental results show that: (1) FL performs worse than centralized approaches when dealing with non-linear data distributions. (2) The use of appropriate detrending techniques improves FL performance, reducing loss across different data distributions.