PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data Structures Across Nodes
This addresses the challenge of leveraging distributed temporal data with varying granularities and variable sets for organizations needing privacy-preserving forecasting, representing a novel method for a known bottleneck.
The paper tackles the problem of federated time series forecasting with heterogeneous data structures across nodes, proposing PiXTime which achieves state-of-the-art performance in federated settings and demonstrates superior results on eight real-world benchmarks.
Time series are highly valuable and rarely shareable across nodes, making federated learning a promising paradigm to leverage distributed temporal data. However, different sampling standards lead to diverse time granularities and variable sets across nodes, hindering classical federated learning. We propose PiXTime, a novel time series forecasting model designed for federated learning that enables effective prediction across nodes with multi-granularity and heterogeneous variable sets. PiXTime employs a personalized Patch Embedding to map node-specific granularity time series into token sequences of a unified dimension for processing by a subsequent shared model, and uses a global VE Table to align variable category semantics across nodes, thereby enhancing cross-node transferability. With a transformer-based shared model, PiXTime captures representations of auxiliary series with arbitrary numbers of variables and uses cross-attention to enhance the prediction of the target series. Experiments show PiXTime achieves state-of-the-art performance in federated settings and demonstrates superior performance on eight widely used real-world traditional benchmarks.