Data acquisition for improving machine learning models
Bibliographic record
Abstract
The vast advances in Machine Learning (ML) over the last ten years have been powered by the availability of suitably prepared data for training purposes. The future of ML-enabled enterprise hinges on data. As such, there is already a vibrant market offering data annotation services to tailor sophisticated ML models. In this paper, inspired by the recent vision of online data markets and associated market designs, we present research on the practical problem of obtaining data in order to improve the accuracy of ML models. We consider an environment in which consumers query for data to enhance the accuracy of their models and data providers who possess data make them available for training purposes. We first formalize this interaction process laying out the suitable framework and associated parameters for data exchange. We then propose two data acquisition strategies that consider a trade-off between exploration during which we obtain data to learn about the distribution of a provider's data and exploitation during which we optimize our data inquiries utilizing the gained knowledge. In the first strategy, Estimation and Allocation (EA), we utilize queries to estimate the utilities of various predicates while learning about the distribution of the provider's data; then we proceed to the allocation stage in which we utilize those learned utility estimates to inform our data acquisition decisions. The second algorithmic proposal, named Sequential Predicate Selection (SPS), utilizes a sampling strategy to explore the distribution of the provider's data, adaptively investing more resources to parts of the data space that are statistically more promising to improve overall model accuracy. We present a detailed experimental evaluation of our proposals utilizing a variety of ML models and associated real data sets exploring all applicable parameters of interest. Our results demonstrate the relative benefits of the proposed algorithms. Depending on the models trained and the associated learning tasks we identify trade-offs and highlight the relative benefits of each algorithm to further optimize model accuracy.
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 | 0.012 | 0.072 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.008 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.005 | 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".