Sari la conținut
aiqbenchInformații despre AI & calcul cuantic
ȘtiriAnalizeBenchmark-uriSkill-uriÎntreabă AIÎnvațăDespre
...Se încarcă sesiunea
ȘtiriAnalizeBenchmark-uriSkill-uriÎntreabă AIÎnvațăDespre

Română · beta. Traducerea a fost făcută automat și este încă în curs de revizuire. Citește pagina în engleză

Înapoi la listă
perspectiva aiqbenchMachine learning

analiza aiqbench

This research introduces Experience Blending, a continual learning framework that uses differential-privacy-inspired noise to generate support boundary data, effectively regularizing decision boundaries to mitigate catastrophic forgetting. By jointly training on exemplars and these boundary-adjacent representations, the method achieves significant accuracy improvements across standard benchmarks like CIFAR-10 and ImageNet1K. The approach offers a robust alternative to standard experience replay by enriching the feature space near critical decision thresholds.
1
Sursă care acoperăarXiv

Continual Learning with Support Boundary Experience Blending

arXiv·12 iunie 2026·2 min de citit·Articolul și perspectiva sunt în engleză.

De la arXiv

Text integral

arXiv:2507.23534v3 Announce Type: replace Abstract: Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy.

EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

Abstract:Continual learning (CL) seeks to mitigate catastrophic forgetting when models are trained with sequential tasks. A common approach, experience replay (ER), stores past exemplars but only sparsely approximates the data distribution, yielding fragile and oversimplified decision boundaries. We address this limitation by introducing Support Boundary Data (SBD), generated via differential-privacy-inspired noise into latent features to create boundary-adjacent representations that implicitly regularize decision boundaries. Building on this idea, we propose Experience Blending (EB), a framework that jointly trains on exemplars and SBD through a dual-model aggregation strategy.

EB has two components: (1) latent-space noise injection to generate support boundary data, and (2) end-to-end training that jointly leverages exemplars and SBD. Unlike standard experience replay, SBD enriches the feature space near decision boundaries, leading to more stable and robust continual learning. Extensive experiments on CIFAR-10, CIFAR-100, Tiny ImageNet, and ImageNet1K demonstrate consistent accuracy improvements of 10%, 6%, 13%, 2%, respectively.

Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV)

arXiv:2507.23534 [cs.LG]

(or arXiv:2507.23534v3 [cs.LG] for this version)

Text integral sub licența deschisă a publicației · 165 cuvinte

Citește pe arXiv ↗Întreabă despre acest articol

Subiecte conexe

Produse AI

EvoLib: Turning experience into evolving knowledge

Microsoft Research · 30 iul. 2026

Cercetare AI

Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction

arXiv · 7 oct. 2026

Cercetare AI

REVOLVE: An Automated Closed-Loop Framework for Evolving Robot Manipulation with Minimal Human Intervention

arXiv · 15 sept. 2026

Cercetare AI

Beyond Episodic Recall: Experience-to-Knowledge Evolution for Lifelong Embodied Navigation

arXiv · 18 nov. 2026

Article info

Source

arXiv

Published

12 iunie 2026

Read time

2 min

Category

Machine learning
aiqbench
Informații despre AI & calcul cuantic© aiqbench. Toate drepturile rezervate.

Fluxuri:RSS·JSON Feed

LimbăEnglish·Românăbeta
ȘtiriAI & tehnologieCuanticAnalize
ExploreazăBenchmark-uriÎnvață
CompanieDespreÎncredereInformații legaleTermeni și condițiiPolitica de confidențialitateNotificări privind drepturile de autorȘtergerea datelorRaportează conținut

Perspectiva aiqbench, analizele, rezumatul zilnic și răspunsurile din Întreabă sunt scrise de modele AI din sursele afișate, fără revizuire editorială înainte de publicare. Pot conține erori — verifică sursa. Cum este folosit modelul →

  • Știri
  • Analize
  • Întreabă
  • Topuri
  • Cont