Research map / Label-efficient and robust learning / Recognition and long-tail
Imbalance Trouble: Revisiting Neural-Collapse Geometry
Christos Thrampoulidis, Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia
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 |
|---|---|---|---|
| measure convergence to SELI geometry instead of ETF geometry | deep nets (ResNet-18, VGG-13) · STEP-imbalanced MNIST, Fashion-MNIST, CIFAR10 | distance to geometry (classifiers, embeddings, logits) | Improved |
| increase imbalance ratio R (up to 100) | deep nets · STEP-imbalanced MNIST, Fashion-MNIST, CIFAR10 | convergence rate to SELI | Hurt |
| measure SELI vs ETF for SGD on the unconstrained feature model | UFM trained with SGD · synthetic UFM, k=4 | distance to geometry | Improved |
| vanishing ridge regularization in the UFM (ablation) | UFM global minimizers · synthetic UFM, k=4 | distance to SELI | Improved |
| increase imbalance ratio R in UFM regularization path (ablation) | UFM global minimizers · synthetic UFM, k=4 | rate of convergence to SELI as lambda vanishes | Hurt |
| classifier versus embedding geometry | deep nets and UFM · STEP-imbalanced datasets | convergence to SELI | Mixed |
Closest papers by meaning
- Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model (ICML 2024 · similarity 0.92)
- Neural Collapse To Multiple Centers For Imbalanced Data (NeurIPS 2024 · similarity 0.90)
- Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model (NeurIPS 2025 · similarity 0.90)
- Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective (NeurIPS 2024 · similarity 0.89)
- Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime (ICML 2025 · similarity 0.89)
- Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame (NeurIPS 2024 · similarity 0.89)
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.
