mlsanityData to 14 Oct 2026

A Channel Coding Benchmark for Meta-Learning

arXiv 2107.07579 ↗First posted 15 Jul 2021cs.LG cs.AI cs.ITcited by 6

Not on the map. Why?

Abstract (arXiv)

Meta-learning provides a popular and effective family of methods for data-efficient learning of new tasks. However, several important issues in meta-learning have proven hard to study thus far. For example, performance degrades in real-world settings where meta-learners must learn from a wide and potentially multi-modal distribution of training tasks; and when distribution shift exists between meta-train and meta-test task distributions. These issues are typically hard to study since the shape of task distributions, and shift between them are not straightforward to measure or control in standard benchmarks. We propose the channel coding problem as a benchmark for meta-learning. Channel coding is an important practical application where task distributions naturally arise, and fast adaptation to new tasks is practically valuable. We use our MetaCC benchmark to study several aspects of meta-learning, including the impact of task distribution breadth and shift, which can be controlled in the coding problem. Going forward, MetaCC provides a tool for the community to study the capabilities and limitations of meta-learning, and to drive research on practically robust and effective meta-learners.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 32 of its 67 references that are in the map. First posted on arXiv 15 Jul 2021.

Builds on

32 of 67 references.

References · 32

  1. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  6. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2020In Search of Lost Domain Generalizationcited by 1,054
  9. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  10. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  11. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
20 more
  1. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  2. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  3. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 315
  4. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  5. 2017An Introduction to Deep Learning for the Physical Layercited by 233
  6. 2020LEEP: A New Measure to Evaluate Transferability of Learned Representationscited by 188
  7. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  8. 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
  9. 2017Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environmentscited by 108
  10. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  11. 2019Meta-Learning with Warped Gradient Descentcited by 98
  12. 2019Meta-Curvaturecited by 70
  13. 2020learn2learn: A Library for Meta-Learning Researchcited by 69
  14. 2020Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Taskscited by 47
  15. 2018Communication Algorithms via Deep Learningcited by 42
  16. 2018Deepcode: Feedback Codes via Deep Learningcited by 42
  17. 2019Learning to Demodulate from Few Pilots via Offline and Online Meta-Learningcited by 21
  18. 2020Regularizing Meta-Learning via Gradient Dropoutcited by 15
  19. 2019MIND: Model Independent Neural Decodercited by 11
  20. 2020End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learningcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 0; 2025: 0; 2026: 1.

6 papers.

  1. 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
  2. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  3. 2023Meta Omnium: A Benchmark for General-Purpose Learning-to-Learncited by 4
  4. 2021Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalizationcited by 2
  5. 2021RELDEC: Reinforcement Learning-Based Decoding of Moderate Length LDPC Codescited by 1
  6. 2026A 3GPP-Compliant Benchmark Dataset for RIS-Aided Beyond 5G Networkscited by 0