Surrogate Data Source Transfer (SDST): An Efficient Transfer Learning Approach for Time Series Forecasting
Bibliographic record
Abstract
Time series prediction plays a crucial role in optimizing the operation of communication networks. Applications of time series prediction include traffic prediction, channel state prediction, handover prediction, etc. However, training high-quality models for these tasks requires large volumes of historical data. This requirement may not be available in some scenarios. In this case, instance-based Transfer Learning (TL) comes as a prominent solution for this problem. However, a few concerns could be raised such as: 1) the time and bandwidth resources consumed in the transfer, 2) it will be hard to specify the amount of data to be transferred, and 3) in case of transferring a subset of the data, which subset is better to transfer. To address these challenges, we propose a novel approach for TL, which is similar to, but different than, instance-based TL based on generative models. We coined the new approach as Surrogate Data Source Transfer (SDST), in which a generative model is trained on the source task. We then transfer the model to the target task (with limited historical data). Extensive experiments confirm the superior performance of the proposed approach in terms of prediction accuracy and consumed resources (time and bandwidth). Our TL approach reduced the mean absolute percentage error (MAPE) by a margin that hits 81% in some datasets. For the source code and data, we refer to the repository https://github.com/MoeR3za/Korsahy_TGAN.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.008 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".