# Deep Meta-Learning: Learning to Learn in the Concept Space

arXiv: https://arxiv.org/abs/1802.03596 · HTML: https://mlsanity.com/paper/1802.03596/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Feb 2018.

## Built on by (most cited first, 22 of 22)

- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs](https://mlsanity.com/paper/2110.13361/) (2021)
- [Few-Shot Learning Meets Transformer: Unified Query-Support Transformers for Few-Shot Classification](https://mlsanity.com/paper/2208.12398/) (2022)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [On Enforcing Better Conditioned Meta-Learning for Rapid Few-Shot Adaptation](https://mlsanity.com/paper/2206.07260/) (2022)
- [Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning](https://mlsanity.com/paper/2103.03901/) (2021)
- [Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks](https://mlsanity.com/paper/2210.12669/) (2022)
- [Meta-Learning with Adjoint Methods](https://mlsanity.com/paper/2110.08432/) (2021)
- [A New First-Order Meta-Learning Algorithm with Convergence Guarantees](https://mlsanity.com/paper/2409.03682/) (2024)
- [3D Meta-Segmentation Neural Network](https://mlsanity.com/paper/2110.04297/) (2021)
- [Generalizing Supervised Deep Learning MRI Reconstruction to Multiple and Unseen Contrasts using Meta-Learning Hypernetworks](https://mlsanity.com/paper/2307.06771/) (2023)
- [Meta-Learning with Heterogeneous Tasks](https://mlsanity.com/paper/2410.18894/) (2024)
- [GCCN: Global Context Convolutional Network](https://mlsanity.com/paper/2110.11664/) (2021)
- [Meta Adversarial Perturbations](https://mlsanity.com/paper/2111.10291/) (2021)
- [A formal definition and meta-model for a machine theory of mind](https://mlsanity.com/paper/2606.03471/) (2026)
- [A Transductive Maximum Margin Classifier for Few-Shot Learning](https://mlsanity.com/paper/2107.11975/) (2021)
- [Urdu Speech and Text Based Sentiment Analyzer](https://mlsanity.com/paper/2207.09163/) (2022)
- [Learning Primitive-aware Discriminative Representations for Few-shot Learning](https://mlsanity.com/paper/2208.09717/) (2022)
- [Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Data](https://mlsanity.com/paper/2309.00647/) (2023)
- [Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning](https://mlsanity.com/paper/2505.07921/) (2025)

## Abstract (arXiv)

Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose deep meta-learning to integrate the representation power of deep learning into meta-learning. The framework is composed of three modules, a concept generator, a meta-learner, and a concept discriminator, which are learned jointly. The concept generator, e.g. a deep residual net, extracts a representation for each instance that captures its high-level concept, on which the meta-learner performs few-shot learning, and the concept discriminator recognizes the concepts. By learning to learn in the concept space rather than in the complicated instance space, deep meta-learning can substantially improve vanilla meta-learning, which is demonstrated on various few-shot image recognition problems. For example, on 5-way-1-shot image recognition on CIFAR-100 and CUB-200, it improves Matching Nets from 50.53% and 56.53% to 58.18% and 63.47%, improves MAML from 49.28% and 50.45% to 56.65% and 64.63%, and improves Meta-SGD from 53.83% and 53.34% to 61.62% and 66.95%, respectively.