Research map / Label-efficient and robust learning / Recognition and long-tail
Meta Learning in Decentralized Neural Networks: Towards More General AI
Yuwei Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Segment local models by performance and train a separate global model for each group | Segmented-FL · Intrusion detection tasks with non-iid data | performance | Improved |
| Align local-model features with embedding matching and a global feature disentangler | Proposed domain adaptation method · Image classification and natural language sentiment classification | transfer learning performance | Improved |
| Add consensus-based voting to produce pseudo-labels | Proposed domain adaptation method · Image classification and natural language sentiment classification | global model performance | Improved |
| Learn a globally shared policy with reinforcement learning and a local model acting as meta | Homogeneous learning for self-attention decentralized deep learning · Image classification | total training time: 50.8\% reduction | Improved |
Closest papers by meaning
- Meta-Learning in Neural Networks: A Survey (TPAMI 2021 · similarity 0.90)
- Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm (ICLR 2018 · similarity 0.87)
- When Meta-Learning Meets Online and Continual Learning: A Survey (TPAMI 2024 · similarity 0.86)
- Meta-Neighborhoods (NeurIPS 2020 · similarity 0.86)
- Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL (ICLR 2019 · similarity 0.86)
- Decentralised Learning with Random Features and Distributed Gradient Descent (ICML 2020 · similarity 0.86)
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.
