Leveraging Multi-Channel Image Representations to Enhance Robustness in Tabular Data Classification
Bibliographic record
Abstract
This paper presents TabImgF, a novel deep tabular data modeling architecture designed for classification tasks involving categorical features. The method adopts a dual-branch strategy to process categorical and continuous features separately. Specifically, categorical features are first transformed into multi-channel image representations using an ImgEncoding module, followed by a convolutional neural network that captures combinatorial patterns and high-level semantic representations. Continuous features are encoded using a fully connected network. The outputs of both branches are concatenated and passed into a classification head, enabling end-to-end training and prediction. Experimental results on five public datasets show that TabImgF achieves at least a 1.8% improvement in average AUC over state-of-the-art deep learning methods and outperforms leading tree-ensemble models. Robustness experiments further demonstrate that TabImgF maintains strong performance in the presence of missing or noisy categorical inputs, confirming its stability and applicability in complex scenarios.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.005 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.007 | 0.004 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".