Summary of Tackling Data Heterogeneity in Federated Time Series Forecasting, by Wei Yuan et al.
Tackling Data Heterogeneity in Federated Time Series Forecasting
by Wei Yuan, Guanhua Ye, Xiangyu Zhao, Quoc Viet Hung Nguyen, Yang Cao, Hongzhi Yin
First submitted to arxiv on: 24 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a novel framework called Fed-TREND for addressing data heterogeneity in time series forecasting with federated learning. The authors highlight that existing methods rely on centralized training paradigms, which overload communication networks and raise privacy concerns. They introduce two types of synthetic data: one to enhance clients’ local training consensus and another to refine the global model after aggregation. Fed-TREND is compatible with most time series forecasting models and can be integrated into existing federated learning frameworks. The paper presents extensive experiments on eight datasets, using several baselines and four popular time series forecasting models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us make better predictions about things like energy use or weather patterns by making sure our computers don’t have to collect all the data in one place. Right now, we do that and it’s causing problems with communication networks and people’s privacy. The authors suggest a new way to work together on this problem, called Fed-TREND, which uses special fake data to help computers learn from each other. They show that this works well on lots of different datasets and models. |
Keywords
» Artificial intelligence » Federated learning » Synthetic data » Time series
