Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Gradual Forgetting

Gradual forgetting is a machine learning technique used in dynamic environments and streaming data processing where the influence of past observations or previously learned knowledge is progressively reduced over time to adapt to evolving data distributions and concept drift. Instead of abruptly discarding all historical information, the system applies continuous decay factors or time-dependent weighting functions that assign greater significance to newer data points while smoothly diminishing the impact of older records. This mechanism enables predictive models to continuously track shifting trends and update their parameters to reflect the current state of non-stationary environments without destabilizing performance through abrupt data loss.

1 item

DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation

DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation

Wendi Li, Xiao Yang, Weiqing Liu, Yingce Xia, Jiang Bian

OrganizationsMicrosoftUniversity of Wisconsin Madison

Why you should read this

Proposes DDG-DA, a proactive adaptation framework that forecasts future streaming data distributions and resamples historical samples via a differentiable distribution distance to train predictive models before concept drift occurs.

In many real-world scenarios, we often deal with streaming data that is sequentially collected over time. Due to the non-stationary nature of the environment, the streaming data distribution may change in unpredictable ways, which is known as concept drift. To handle concept drift, previous methods first detect when/where the concept drift happens and then adapt models to fit the distribution of the latest data. However, there are still many cases that some underlying factors of environment evolution are predictable, making it possible to model the future concept drift trend of the streaming data, while such cases are not fully explored in previous work. In this paper, we propose a novel method DDG-DA, that can effectively forecast the evolution of data distribution and improve the performance of models. Specifically, we first train a predictor to estimate the future data distribution, then leverage it to generate training samples, and finally train models on the generated data. We conduct experiments on three real-world tasks (forecasting on stock price trend, electricity load and solar irradiance) and obtain significant improvement on multiple widely-used models.

Added

2026-09-26