Resampling Framework Based on Swarm Intelligence Optimization for Imbalanced Data Classification
Bibliographic record
Abstract
In recent years, swarm intelligence optimization (SIO) algorithms have developed rapidly and are widely applied, particularly in classification tasks. The challenge of imbalanced data is a critical issue in classification, as it negatively impacts classification performance. Resampling techniques have been proposed to address this problem, but their classical approaches leave room for improvement, making applying SIO algorithms to resampling an effective solution. Optimizing resampling results is generally considered a combinatorial optimization process. Therefore, few continuous SIO algorithms have been applied to find the optimal resampling result, making it necessary to propose a unified application framework for them. This paper proposes the Resampling Framework Based on Swarm Intelligence Optimization for Imbalanced Data Classification (R-SIOIC). R-SIOIC supports the application of any continuous SIO algorithm for resampling. It optimizes multiple resampling results in each iteration, ultimately producing the optimal resampling result. This paper selects three continuous SIO algorithms to evaluate the effectiveness of R-SIOIC. The experiments used 13 imbalanced datasets, and compared the results with those from 13 baseline methods and the original data input without resampling. R-SIOIC outperformed all other methods on 11 out of 13 datasets for G-mean and 12 out of 13 datasets for m-AUC, demonstrating its superior performance.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".