Skip to content
AI News HubLIVE
Original source2 min read

Model Annealing: Data-Efficient Learning through Review and Consolidation

Summary

This paper introduces model annealing, a training method that uses the remaining budget for review and consolidation by relearning from the network's own knowledge via reheated episodes, a prediction memory, and adversarial dreams, improving accuracy, calibration, and robustness across datasets and architectures without extra inference cost.

SourcearXiv AIAuthor: Ali Mohammadi Ruzbahani, Rezvan Abouzadeh
Model Annealing: Data-Efficient Learning through Review and Consolidation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Nov 2026]

Title:Model Annealing: Data-Efficient Learning through Review and Consolidation

View a PDF of the paper titled Model Annealing: Data-Efficient Learning through Review and Consolidation, by Ali Mohammadi Ruzbahani and 1 other authors

View PDF HTML (experimental)

Abstract:A small labelled dataset is memorized long before the training budget runs out, and the one-hot labels that remain to be fitted then mostly sharpen confidence. Model annealing spends the rest of the budget on review and consolidation, relearning from the network's own knowledge. Training is divided into episodes whose learning rate is raised again and cooled, every cooled state joins a memory of past selves, and each new episode learns from the labels, from the tempered predictions of this memory, and from adversarial dreams sought where student and memory disagree most. The memory averages predictions rather than weights, and the deployed network is the last student, so inference costs nothing extra. Across CIFAR-100, Tiny-ImageNet and Imagewoof, four architecture families and 5\% to 100\% of the labels, model annealing raises the top-1 accuracy of the AdamW-trained ConvNeXt, ViT and MLP-Mixer over cross-entropy training in 28 of 33 configurations, by 1.3 points on average, and is on par in accuracy with snapshot distillation, the closest competitor. On these families it is better than both in likelihood, calibration and robustness to corruptions and small adversarial perturbations. For an SGD-trained ResNet-18 it lowers accuracy but still improves robustness to small adversarial perturbations. Separating the reheated schedule from relearning shows that relearning helps every family and that the losses come from reheats, which undo most of this network's fit to its training set. How early the accuracy of a cross-entropy run saturates largely separates the AdamW families from ResNet-18 but does not predict the gain within them. With little data, relearning from the latest snapshot without dreams, as snapshot distillation does, compounds overconfidence in the AdamW families from episode to episode. The memory and the dreams each curb most of this drift, and together they remove it.

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2611.17524 [cs.AI]

(or arXiv:2611.17524v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.17524

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Rezvan Abouzadeh [view email] [v1] Thu, 12 Nov 2026 21:19:26 UTC (277 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Model Annealing: Data-Efficient Learning through Review and Consolidation, by Ali Mohammadi Ruzbahani and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • Model annealing divides training into episodes with re-raised and cooled learning rates; each cooled state joins a memory, and new episodes learn from labels, tempered memory predictions, and adversarial dreams where student and memory disagree.
  • On CIFAR-100, Tiny-ImageNet, and Imagewoof, it raises top-1 accuracy for AdamW-trained ConvNeXt, ViT, and MLP-Mixer in 28 of 33 configurations by 1.3 points on average, on par with snapshot distillation.
  • It improves likelihood, calibration, and robustness to corruptions and small adversarial perturbations over both cross-entropy and snapshot distillation; the deployed network is the last student, so inference costs nothing extra.
  • Separating reheats from relearning shows relearning helps every family while losses come from reheats; memory and dreams together eliminate overconfidence drift in low-data regimes.

Highlights and analysis are generated automatically and may contain errors. Check the original source.