From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity

Documenti analoghi

• Class-wise Balancing Data Replay for Federated Class-Incremental Learning
  di: Qi, Zhuang, et al.
  Pubblicazione: (2025)
• Federated Cross-Training Learners for Robust Generalization under Data Heterogeneity
  di: Qi, Zhuang, et al.
  Pubblicazione: (2024)
• Global Intervention and Distillation for Federated Out-of-Distribution Generalization
  di: Qi, Zhuang, et al.
  Pubblicazione: (2025)
• Federated Deconfounding and Debiasing Learning for Out-of-Distribution Generalization
  di: Qi, Zhuang, et al.
  Pubblicazione: (2025)
• Semantic-Space-Intervened Diffusive Alignment for Visual Classification
  di: Li, Zixuan, et al.
  Pubblicazione: (2025)