Research map / Federated learning and privacy / Personalized and heterogeneous FL
Heterogeneity-aware Distillation for Federated Continual Learning
Gaozhuo Liu, Yichen Li, Xiuying Wang, Yulong Li, Chuang Zhao, Yankai Jiang, Imran Razzak
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Revisits heterogeneity in federated continual learning, separating spatial static heterogeneity (data distribution and architecture differences across clients) from temporal dynamic heterogeneity (task shifts over time), and proposes a heterogeneity-aware distillation approach.
Problem
Federated continual learning requires distributed clients to learn new tasks while retaining old knowledge, and must cope with both spatial (static, across clients) and temporal (dynamic, across tasks) heterogeneity.
Approach
Decomposes FCL heterogeneity into spatial static and temporal dynamic components and uses distillation tailored to each; the abstract is truncated, so the specific mechanism is not stated.
Closest papers by meaning
- Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor (CVPR 2025 · similarity 0.92)
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning (NeurIPS 2026 · similarity 0.91)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.91)
- Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning (NeurIPS 2025 · similarity 0.89)
- Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning (NeurIPS 2025 · similarity 0.88)
- Resource-Constrained Federated Continual Learning: What Does Matter? (NeurIPS 2025 · similarity 0.88)
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.
