A Channel Coding Benchmark for Meta-Learning

Abstract

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.

References in corpus (17)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• mixup: Beyond Empirical Risk Minimization
• Estimating Mutual Information
• Theoretical Models of Learning to Learn
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• On First-Order Meta-Learning Algorithms
• Similarity of Neural Network Representations Revisited
• Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Learning to Demodulate from Few Pilots via Offline and Online Meta-Learning
• Feature-Critic Networks for Heterogeneous Domain Generalization
• LEEP: A New Measure to Evaluate Transferability of Learned Representations
• Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation
• BOIL: Towards Representation Change for Few-shot Learning
• End-to-End Fast Training of Communication Links Without a Channel Model via Online Meta-Learning
• When MAML Can Adapt Fast and How to Assist When It Cannot

Cited by in corpus (1)

• Bayesian Active Meta-Learning for Few Pilot Demodulation and Equalization