Pith. sign in

REVIEW 6 cited by

Neural Collapse: A Review on Modelling Principles and Generalization

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.04041 v2 pith:W2DMPBNR submitted 2022-06-08 cs.LG

Vignesh Kothapalli This is my paper · ORCID
classification cs.LG
keywords neuralcollapsestategeneralizationimplicationslayermodellingnetworks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the within-class variability of final hidden layer outputs is infinitesimally small and their class means form a simplex equiangular tight frame. This simplifies the last layer behaviour to that of a nearest-class center decision rule. Despite the simplicity of this state, the dynamics and implications of reaching it are yet to be fully understood. In this work, we review the principles which aid in modelling neural collapse, followed by the implications of this state on generalization and transfer learning capabilities of neural networks. Finally, we conclude by discussing potential avenues and directions for future research.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 12 citations worldwide. Full citation record

  1. How to Tame Grokking: Representation Geometry as a Control Signal

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Dimensionality collapse precedes grokking; GeomDR, a spectral regularizer on hidden covariances, accelerates it up to 52× on modular and permutation tasks for MLPs and transformers.

  2. FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios

    cs.LG 2025-07 reject novelty 6.0 of 10

    FedWCM uses per-client data-distribution scores to adapt momentum and aggregation weights in federated learning, showing empirical gains over FedAvg and FedCM on long-tailed non-IID datasets, but its convergence proof...

  3. Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A two-stage alignment framework that first fuses visual modalities (RGB, flow, skeleton) then introduces text, achieving 21% SRCC improvement on a new clinical AQA dataset and gains on two public benchmarks.

  4. The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations

    cs.LG 2025-07 conditional novelty 5.0 of 10

    FACT is a first-order stationarity identity for weight matrices that matches or beats the Neural Feature Ansatz as a description of learned features at convergence.

  5. Feature learning is decoupled from generalization in high capacity neural networks

    cs.LG 2025-07 conditional novelty 4.0 of 10

    Current feature learning measures quantify the magnitude of representation change, which the authors argue is decoupled from the generalization benefit that neural networks show over their neural tangent kernel.

  6. Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets

    cs.CV 2025-05 conditional novelty 4.0 of 10

    Combining neural-collapse feature alignment with classifier weight balancing improves closed-set and open-set accuracy for long-tailed medical image classification under semi-supervised learning.

Pith tools