Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting

Gang Chen, Hua Lu, Yuxuan Liang, Huan Li, Yuxuan Yang, Dalin Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• SuDIS-ZJU/SCAM

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Time Series Forecasting (TSF) is a crucial task in various domains, yet existing TSF models rely heavily on high-quality data and insufficiently exploit all available data. This paper explores a novel self-supervised approach to re-label time series datasets by inherently constructing candidate datasets. During the optimization of a simple reconstruction network, intermediates are used as pseudo labels in a self-supervised paradigm, improving generalization for any predictor. We introduce the Self-Correction with Adaptive Mask (SCAM), which discards overfitted components and selectively replaces them with pseudo labels generated from reconstructions. Additionally, we incorporate Spectral Norm Regularization (SNR) to further suppress overfitting from a loss landscape perspective. Our experiments on eleven real-world datasets demonstrate that SCAM consistently improves the performance of various backbone models. This work offers a new perspective on constructing datasets and enhancing the generalization of TSF models through self-supervised learning. The code is available at https://github.com/SuDIS-ZJU/SCAM. 1. Can the reliance on high-quality labeled time series datasets be alleviated, given their scarcity?

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.14704")
get_code_for_paper("2502.14704")
have("2502.14704")

Connect an agent — have() is free.