Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
A Channel Coding Benchmark for Meta-Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use adaptive meta-learned decoding rather than a non-adaptive ERM decoder | Channel decoding on the real wireless channel · MetaCC real wireless channel | error rate: 58\% reduction | Helped |
| Use adaptive meta-learned decoding rather than Viterbi | Channel decoding on the real wireless channel · MetaCC real wireless channel | error rate: 30\% reduction | Helped |
| Train on a broader multi-family task distribution instead of a focused within-family distribution | Meta-learners · Bursty and Multipath target channels | BER | Hurt |
| Expand the training distribution within a single channel family | Meta-learners · Within-family MetaCC tests | BER | No clear effect |
| Increase training task-distribution diversity | Meta-learners relative to ERM · MetaCC channel families | accuracy gain over ERM | Helped |
| Evaluate on tasks shifted away from the meta-training distribution | Meta-learners · MetaCC train-test distribution shift | absolute decoding performance | Hurt |
| Increase train-test task-distribution distance | Meta-learners relative to ERM · MetaCC channel families | accuracy improvement over ERM | Helped |
| Reduce the number of unique training channel domains | Most meta-learners · MetaCC, 100, 50, or 20 unique domains | accuracy | Hurt |
| Use MetaSGD or MetaCurvature rather than weaker meta-learners | Adaptive channel decoding · MetaCC aggregate experiments | overall performance | Helped |
Closest papers by meaning
- Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation (ICLR 2024 · similarity 0.88)
- Meta-Learning of Structured Task Distributions in Humans and Machines (ICLR 2021 · similarity 0.88)
- A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm (NeurIPS 2023 · similarity 0.87)
- Learning to Propagate for Graph Meta-Learning (NeurIPS 2019 · similarity 0.87)
- An Information-Theoretic Analysis of In-Context Learning (ICML 2024 · similarity 0.86)
- Learning to Learn with Contrastive Meta-Objective (NeurIPS 2025 · 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.