Research map / Label-efficient and robust learning / Test-time adaptation
DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Predict future distribution and resample historical training data accordingly | LightGBM forecasting with DDG-DA · Stock Price Trend Forecasting | IC: 0.1178 -> 0.1312 | Helped |
| Predict future distribution and resample historical training data accordingly | LightGBM forecasting with DDG-DA · Electricity Load | NMAE: 0.1877 -> 0.1622 | Helped |
| Predict future distribution and resample historical training data accordingly | LightGBM forecasting with DDG-DA · Solar Irradiance | MAE: 21.7704 -> 18.7997 | Helped |
| Use DDG-DA rather than exponential gradual forgetting | LightGBM forecasting · Stock Price Trend Forecasting | IC: 0.1234 -> 0.1312 | Helped |
| Use DDG-DA rather than exponential gradual forgetting | LightGBM forecasting · Electricity Load | NMAE: 0.1839 -> 0.1622 | Helped |
| Use DDG-DA rather than exponential gradual forgetting | LightGBM forecasting · Solar Irradiance | MAE: 21.6841 -> 18.7997 | Helped |
| Apply DDG-DA resampling | Linear forecasting model · Stock Price Trend Forecasting | IC: 0.0863 -> 0.0971 | Helped |
| Apply DDG-DA resampling | MLP forecasting model · Stock Price Trend Forecasting | IC: 0.1091 -> 0.1211 | Helped |
| Apply DDG-DA resampling | LSTM forecasting model · Stock Price Trend Forecasting | IC: 0.1008 -> 0.1049 | Helped |
| Apply DDG-DA resampling | GRU forecasting model · Stock Price Trend Forecasting | IC: 0.1182 -> 0.1183 | No clear effect |
| Use GHO optimization and an MLP proxy model instead of DDG-DA's closed-form linear proxy (ablation) | DDG-DA · Stock Price Trend Forecasting | IC: 0.1211 -> 0.1204 | Hurt |
| Use DDG-DA for random abrupt, unpredictable concept drift | DDG-DA · Four generated regression datasets | forecast-label correlation | Hurt |
Closest papers by meaning
- Identifying Predictions That Influence the Future: Detecting Performative Concept Drift in Data Streams (AAAI 2025 · similarity 0.85)
- RCCDA: Adaptive Model Updates in the Presence of Concept Drift under a Constrained Resource Budget (NeurIPS 2025 · similarity 0.85)
- Early Concept Drift Detection via Prediction Uncertainty (AAAI 2025 · similarity 0.85)
- Quilt: Robust Data Segment Selection against Concept Drifts (AAAI 2024 · similarity 0.83)
- Cherry-Picking in Time Series Forecasting: How to Select Datasets to Make Your Model Shine (AAAI 2025 · similarity 0.83)
- Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.