Research map / Label-efficient and robust learning / Recognition and long-tail
Data Augmentation for Compositional Data: Advancing Predictive Models of the Microbiome
Elliott Gordon-Rodriguez, Thomas P Quinn, John Patrick Cunningham
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add Aitchison Mixup to supervised microbiome classifiers | Random Forest, XGBoost, mAML, DeepCoDa, and MetaNN · Microbiome benchmark (12 tasks) | ROC AUC: 0.77 -> 0.79; 0.78 -> 0.80; 0.78 -> 0.79; 0.75 -> 0.80; 0.74 -> 0.74 | Improved |
| Add Random Subcompositions to supervised microbiome classifiers | Random Forest, XGBoost, mAML, DeepCoDa, and MetaNN · Microbiome benchmark (12 tasks) | ROC AUC: 0.77 -> 0.79; 0.78 -> 0.79; 0.78 -> 0.78; 0.75 -> 0.78; 0.74 -> 0.75 | Improved |
| Add Compositional CutMix to supervised microbiome classifiers | Random Forest, XGBoost, mAML, DeepCoDa, and MetaNN · Microbiome benchmark (12 tasks) | ROC AUC: 0.77 -> 0.79; 0.78 -> 0.80; 0.78 -> 0.79; 0.75 -> 0.80; 0.74 -> 0.75 | Improved |
| Use contrastive pretraining with Random Subcompositions instead of no pretraining | DeepMicro encoder · Microbiome benchmark (12 tasks), linear evaluation | ROC AUC: 0.72 -> 0.78 | Improved |
| Use contrastive pretraining with Random Subcompositions instead of DeepMicro reconstruction pretraining | DeepMicro encoder · Microbiome benchmark (12 tasks), linear evaluation | ROC AUC: 0.75 -> 0.78 | Improved |
| Use contrastive pretraining with Random Subcompositions instead of DeepMicro reconstruction pretraining | DeepMicro encoder · Microbiome benchmark (12 tasks), finetuning | ROC AUC: 0.76 -> 0.77 | Improved |
| Replace Random Subcompositions with Aitchison Mixup in contrastive pretraining (ablation) | Contrastive representation learning · Microbiome benchmark (12 tasks), linear evaluation | ROC AUC: 0.72 -> 0.75 | Mixed |
| Replace Random Subcompositions with Compositional CutMix in contrastive pretraining (ablation) | Contrastive representation learning · Microbiome benchmark (12 tasks), linear evaluation | ROC AUC: 0.75 -> 0.78 | Improved |
Closest papers by meaning
- A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features (ICML 2025 · similarity 0.83)
- Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach (AAAI 2024 · similarity 0.82)
- Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression (ICLR 2024 · similarity 0.82)
- SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation (ICLR 2024 · similarity 0.82)
- Prediction-Augmented Trees for Reliable Statistical Inference (NeurIPS 2026 · similarity 0.82)
- TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
