On the combined effect of class imbalance and concept complexity in deep\n learning
Bibliographic record
Abstract
Structural concept complexity, class overlap, and data scarcity are some of\nthe most important factors influencing the performance of classifiers under\nclass imbalance conditions. When these effects were uncovered in the early\n2000s, understandably, the classifiers on which they were demonstrated belonged\nto the classical rather than Deep Learning categories of approaches. As Deep\nLearning is gaining ground over classical machine learning and is beginning to\nbe used in critical applied settings, it is important to assess systematically\nhow well they respond to the kind of challenges their classical counterparts\nhave struggled with in the past two decades. The purpose of this paper is to\nstudy the behavior of deep learning systems in settings that have previously\nbeen deemed challenging to classical machine learning systems to find out\nwhether the depth of the systems is an asset in such settings. The results in\nboth artificial and real-world image datasets (MNIST Fashion, CIFAR-10) show\nthat these settings remain mostly challenging for Deep Learning systems and\nthat deeper architectures seem to help with structural concept complexity but\nnot with overlap challenges in simple artificial domains. Data scarcity is not\novercome by deeper layers, either. In the real-world image domains, where\noverfitting is a greater concern than in the artificial domains, the advantage\nof deeper architectures is less obvious: while it is observed in certain cases,\nit is quickly cancelled as models get deeper and perform worse than their\nshallower counterparts.\n
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 | 0.010 | 0.038 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.003 | 0.007 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".