Suggested books by Mike Jordan at Berkeley:link
- Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference (CVPR2022) [paper]
- Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-Shot Learning (CVPR2022) [paper]
- Ranking Distance Calibration for Cross-Domain Few-Shot Learning (CVPR2022) [paper]
- EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning (CVPR2022) [paper]
- Integrative Few-Shot Learning for Classification and Segmentation (CVPR2022) [paper]
- Semi-Supervised Few-Shot Learning via Multi-Factor Clustering (CVPR2022) [paper]
- Cross-Domain Few-Shot Learning With Task-Specific Adapters (CVPR2022) [paper]
- Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning (CVPR2022) [paper]
- Few-Shot Learning With Noisy Labels (CVPR2022) [paper]
- Meta Convolutional Neural Networks for Single Domain Generalization (CVPR2022) [paper]
- Meta Agent Teaming Active Learning for Pose Estimation (CVPR2022) [paper]
- Meta Distribution Alignment for Generalizable Person Re-Identification (CVPR2022) [paper]
- Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification (CVPR2022) [paper]
- CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification (CVPR2022) [paper]
- Generating Representative Samples for Few-Shot Classification (CVPR2022) [paper]
- Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classification (CVPR2022) [paper]
- Task Discrepancy Maximization for Fine-Grained Few-Shot Classification (CVPR2022) [paper]
- On the Importance of Firth Bias Reduction in Few-Shot Classification (ICLR2022) [paper]
- Continuous-Time Meta-Learning with Forward Mode Differentiation (ICLR2022) [paper]
- Finetuned Language Models are Zero-Shot Learners (ICLR2022) [paper]
- How to Train Your MAML to Excel in Few-Shot Classification (ICLR2022) [paper]
- Task Affinity with Maximum Bipartite Matching in Few-Shot Learning (ICLR2022) [paper]
- Bootstrapped Meta-Learning (ICLR2022) [paper]
- Meta-Learning with Fewer Tasks through Task Interpolation (ICLR2022) [paper]
- Vision-Based Manipulators Need to Also See from Their Hands (ICLR2022) [paper]
- Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners (ICLR2022) [paper]
- Subspace Regularizers for Few-Shot Class Incremental Learning (ICLR2022) [paper]
- ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning (ICLR2022) [paper]
- Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification (ICLR2022) [paper]
- LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 (ICLR2022) [paper]
- Few-shot Learning via Dirichlet Tessellation Ensemble (ICLR2022) [paper]
- Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization (ICLR2022) [paper]
- Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification (ICLR2022) [paper]
- On the Role of Neural Collapse in Transfer Learning (ICLR2022) [paper]
- Generalizing Few-Shot NAS with Gradient Matching (ICLR2022) [paper]
- Neural Variational Dropout Processes (ICLR2022) [paper]
- Hierarchical Few-Shot Imitation with Skill Transition Models (ICLR2022) [paper]
- Learning Prototype-oriented Set Representations for Meta-Learning (ICLR2022) [paper]
- Few-Shot Backdoor Attacks on Visual Object Tracking (ICLR2022) [paper]
- Hierarchical Variational Memory for Few-shot Learning Across Domains (ICLR2022) [paper]
- Prototype memory and attention mechanisms for few shot image generation (ICLR2022) [paper]
- Language-driven Semantic Segmentation (ICLR2022) [paper]
- Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning (ICLR2022) [paper]
- Vector-quantized Image Modeling with Improved VQGAN (ICLR2022) [paper]
- Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators (ICLR2022) [paper]
- Synchromesh: Reliable Code Generation from Pre-trained Language Models (ICLR2022) [paper]
- Knowledge Infused Decoding (ICLR2022) [paper]
- Transformers Can Do Bayesian Inference (ICLR2022) [paper]
- Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning (ICLR2022) [paper]
- Skill-based Meta-Reinforcement Learning (ICLR2022) [paper]
- Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty (ICLR2022) [paper]
- Meta-Imitation Learning by Watching Video Demonstrations (ICLR2022) [paper]
- Learning Prototype-oriented Set Representations for Meta-Learning (ICLR2022) [paper]
- Model-Based Offline Meta-Reinforcement Learning with Regularization (ICLR2022) [paper]
- Hindsight Foresight Relabeling for Meta-Reinforcement Learning (ICLR2022) [paper]
- Contrastive Learning is Just Meta-Learning (ICLR2022) [paper]
- Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty (ICLR2022) [paper]
- Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate (ICLR2022) [paper]
- CoMPS: Continual Meta Policy Search (ICLR2022) [paper]
- Meta-Imitation Learning by Watching Video Demonstrations (ICLR2022) [paper]
- SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search (ICLR2022) [paper]
- Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities (ICLR2022) [paper]
- Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients (ICLR2022) [paper]
- Online Hyperparameter Meta-Learning with Hypergradient Distillation (ICLR2022) [paper]
- Task Relatedness-Based Generalization Bounds for Meta Learning (ICLR2022) [paper]
- Bootstrapped Meta-Learning (ICLR2022) [paper]
- Fast Training of Neural Lumigraph Representations using Meta Learning (NeurIPS2022) [paper]
- Generalization Bounds for Meta-Learning via PAC-Bayes and Uniform Stability (NeurIPS2022) [paper]
- MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images (NeurIPS2022) [paper]
- Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution (NeurIPS2022) [paper]
- Learning where to learn: Gradient sparsity in meta and continual learning (NeurIPS2022) [paper]
- Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks (NeurIPS2022) [paper]
- Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data (NeurIPS2022) [paper]
- Meta-learning with an Adaptive Task Scheduler (NeurIPS2022) [paper]
- Towards Enabling Meta-Learning from Target Models (NeurIPS2022) [paper]
- How Fine-Tuning Allows for Effective Meta-Learning (NeurIPS2022) [paper]
- Meta-Adaptive Nonlinear Control: Theory and Algorithms (NeurIPS2022) [paper]
- Meta-Learning Sparse Implicit Neural Representations (NeurIPS2022) [paper]
- Meta Learning Backpropagation And Improving It (NeurIPS2022) [paper]
- Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning(NeurIPS2022) [paper]
- Noether Networks: meta-learning useful conserved quantities (NeurIPS2022) [paper]
- Statistically and Computationally Efficient Linear Meta-representation Learning (NeurIPS2022) [paper]
- On sensitivity of meta-learning to support data (NeurIPS2022) [paper]
- Meta Internal Learning (NeurIPS2022) [paper]
- Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS2022) [paper]
- Multi-Objective Meta Learning(NeurIPS2022) [paper]
- EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization (NeurIPS2022) [paper]
- Meta-learning to Improve Pre-training (NeurIPS2022) [paper]
- Memory Efficient Meta-Learning with Large Images(NeurIPS2022) [paper]
- Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis (NeurIPS2022) [paper]
- Bayesian decision-making under misspecified priors with applications to meta-learning (NeurIPS2022) [paper]
- Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media(NeurIPS2022) [paper]
- Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS2022) [paper]
- Towards Sample-efficient Overparameterized Meta-learning (NeurIPS2022) [paper]
- Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning (NeurIPS2022) [paper]
- Discovery of Options via Meta-Learned Subgoals (NeurIPS2022) [paper]
- Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks (NeurIPS2022) [paper]
- Meta-Learning for Relative Density-Ratio Estimation (NeurIPS2022) [paper]
[1] Andrychowicz, Marcin, et al. Learning to learn by gradient descent by gradient descent. Advances in Neural Information Processing Systems. 2016. link (使用LSTM学习梯度)
[2] Finn, Chelsea, Pieter Abbeel, and Sergey Levine.Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017.link (二次梯度)
[3] Snell, Jake, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. Advances in Neural Information Processing Systems. 2017.link (四种度量网络的一个)
[4] Lake, Brenden M., Ruslan Salakhutdinov, and Joshua B. Tenenbaum. Human-level concept learning through probabilistic program induction. Science 350.6266 (2015): 1332-1338.link (偏向于特征工程学习先验)
[5] Sung, Flood, et al. Learning to compare: Relation network for few-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.link (四种度量网络的一个)
[6] Vinyals, Oriol, et al. Matching networks for one shot learning. Advances in neural information processing systems. 2016.link (四种度量网络的一个)
[7] Koch, Gregory, Richard Zemel, and Ruslan Salakhutdinov. Siamese neural networks for one-shot image recognition. ICML Deep Learning Workshop. Vol. 2. 2015.link (孪生网络)
[8] Ravi, Sachin, and Hugo Larochelle. Optimization as a model for few-shot learning. (2016).link
[9] Chen, Yutian, et al. Learning to learn without gradient descent by gradient descent. Proceedings of the 34th International Conference on Machine Learning-Volume 70. JMLR. org, 2017.link (梯度优化黑盒函数)
[10] Xu, Ju, and Zhanxing Zhu. Reinforced continual learning. Advances in Neural Information Processing Systems. 2018.link
[11] Pham, Hieu, et al. Efficient neural architecture search via parameter sharing. arXiv preprint arXiv:1802.03268 (2018).link
[12] Elsken, Thomas, Jan Hendrik Metzen, and Frank Hutter. Neural architecture search: A survey. arXiv preprint arXiv:1808.05377 (2018).link (很好的一篇NAS的综述)
[13] Quanming, Yao, et al. Taking human out of learning applications: A survey on automated machine learning. arXiv preprint arXiv:1810.13306 (2018).[link](https://arxiv.org/pdf/1810.13306.pdf (一篇不错的AutoML的综述)
[14] Nichol, Alex, Joshua Achiam, and John Schulman. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999 (2018).link (两篇分析并拓展MAML算法的文章,reptile版本)
[15] Antoniou, Antreas, Harrison Edwards, and Amos Storkey. How to train your MAML. arXiv preprint arXiv:1810.09502 (2018).link (两篇分析并拓展MAML算法的文章)
[16] Frank Hutter, Lars Kotthoff, Joaquin VanschorenAutomatic Machine Learning:Methods, Systems, Challenges .link (automl介绍全面的书)
[17] Dong, Jianfeng, et al. Dual Encoding for Zero-Example Video Retrieval. CVPR, 2019. link (孪生网络在零样本学习的应用,视频检索)
[18] Frans K, Ho J, Chen X, et al. Meta learning shared hierarchies[J]. arXiv preprint arXiv:1710.09767, 2017. link (openai天才高中生)
[19] Wang, Duo, et al. A Hybrid Approach with Optimization-Based and Metric-Based Meta-Learner for Few-Shot Learning. Neurocomputing (2019).link (MAML训练feature extractor,meta classifier做分类)
[20] Yingtian Zou , Jiashi Feng. Hierarchical Meta Learning. arXiv preprint arXiv:1904.09081v1, 2019. link (在MAML的基础上考虑不相似的domain)
[20] Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar. Provable Guarantees for Gradient-Based Meta-Learning. arXiv preprint arXiv:1902.10644, 2019. link (ICML2019)
[21] Meta-Learning: Learning to Learn Fastlink (一个简单介绍元学习STOA方法的博客,主要基于图像分类)
[22] Joaquin Vanschoren. Meta-Learning: A Survey. arXiv preprint arXiv:1810.03548, 2018.link
[23] NIPS2018 accepted meta-learning paper link