A new method for few-shot learning using embedded class models and shot-free meta training.
problem Few-shot learning with limited data and varying number of samples per class.
method Learning embeddings for few-shot learning with embedded class models and shot-free meta training.
result Achieves state-of-the-art performance on standard few-shot benchmark datasets.
New method for incremental meta-learning reduces forgetting and improves performance.
problem Incremental meta-learning for few-shot classification tasks.
method Indirect Discriminant Alignment (IDA) with incremental updates.
result Incremental learning reduces forgetting and improves performance.
Theoretical analysis improves few-shot learning performance.
problem Optimizing the number of labeled examples per category in few-shot learning.
method Theoretical analysis of Prototypical Networks, proposing a robust method to the shot number.
result Model trained for arbitrary meta-training shot number performs well across different meta-testing shot numbers.
Meta-learning bound uses conditional mutual information.
problem Bounding generalization performance in meta-learning.
method Extends CMI framework to meta-learning with a meta-supersample.
result Explicit bound involving two CMI terms.
Paper tackles offline meta-reinforcement learning with a new algorithm.
problem Performing reinforcement learning on limited data from a new task.
method Meta-Actor Critic with Advantage Weighting (MACAW) algorithm.
result Achieves notable gains over prior methods on offline meta-RL benchmarks.
Study on generalization in gradient-based meta-learning, showing flatter solutions and coherence between adaptation trajectories.
problem Understanding generalization in gradient-based meta-learning.
method Analysis of objective landscapes, experimental demonstration of solution properties, and empirical evidence on coherence between adaptation trajectories.
result Meta-test solutions become flatter, lower in loss, and further away from the meta-train solution as meta-training progresses, even as generalization starts to degrade.
Transformers learn to solve various tasks without explicit design.
problem Training models with minimal inductive bias.
method Meta-learning approach to train general-purpose in-context learning algorithms.
result Transformers can be meta-trained to solve a wide range of tasks.
Meta-learning improves feature extraction for few-shot tasks.
problem Understanding why meta-learning models perform better on few-shot classification.
method Developed hypotheses and a regularizer to improve standard training routines.
result Meta-learned models outperform classical training routines in few-shot classification.
Meta learning can adapt fast but is vulnerable to adversarial attacks.
problem Vulnerability of meta learning to adversarial attacks.
method Formal definition of adversarial attacks unique to meta learning, proposing an attacking algorithm.
result Meta learning is vulnerable to adversarial attacks.
Meta-Q-Learning improves meta-Reinforcement Learning using past data.
problem Improving meta-Reinforcement Learning performance.
method Meta-Q-Learning combines Q-learning, multi-task objectives, and off-policy updates to adapt policies from past data.
result Meta-Q-Learning compares favorably with state-of-the-art meta-RL algorithms on benchmarks.
Paper proposes Meta Label Learning to infer global labels for robust few-shot models.
problem Few-shot learning with limited training data.
method Meta Label Learning (MeLa) framework that infers global labels.
result MeLa framework is competitive with existing methods and robust for few-shot learning.
Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depe…
MeLa learns task relations by inferring global labels for robust FSL.
problem Few-shot learning with limited global labels.
method Meta Label Learning (MeLa) and augmented pre-training.
result MeLa outperforms existing methods across diverse benchmarks.
Meta-learning strategy improves few-shot classification performance.
problem Few-shot classification with deep neural networks struggles when labeled samples are limited.
method Proposes an easy-to-hard expert meta-training strategy to arrange training tasks based on task hardness.
result Meta-learners achieve better results with the proposed expert training strategy.
HML improves meta learning for diverse tasks.
problem Few-shot learning with heterogeneous tasks.
method Hierarchical factorization and dual-level training.
result HML outperforms existing methods in generalization.
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…
In this paper, we propose a novel dynamic ensemble selection framework using meta-learning. The framework is divided into three steps. In the first step, the pool of classifiers is generated from the training data. The second phase is responsible to extract the meta-features and train the meta-classifier. Five distinct…
Automates loss function selection for faster, more robust model training.
problem Manual selection of loss functions is inefficient and model-specific.
method Meta-learning to learn parametric loss functions that generalize across tasks.
result Meta-trained loss functions improve model performance in supervised and reinforcement learning.
This paper bounds meta-generalization gap using information theory.
problem Improving sample efficiency for new tasks in meta-learning.
method Information-theoretic upper bounds on meta-generalization gap for two meta-learning classes.
result Novel ITMI bounds for noisy iterative algorithms.
A new approach to meta-RL reduces sample inefficiency.
problem Meta-RL requires impractical amounts of on-policy experience.
method Federated learning approach where off-policy learners solve individual tasks and consolidate solutions into a meta-learner.
result Significant improvements in meta-RL sample efficiency.
New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
MAT combines meta-learning and adversarial training to defend against universal patches.
problem Defending against universal patches that fool models in various contexts.
method Meta adversarial training (MAT) integrates meta-learning with adversarial training.
result MAT increases robustness against universal patch attacks on image classification and traffic-light detection.
HyperX uses reward bonuses to enable efficient exploration in meta-learning.
problem Catastrophic failure of meta-learning with sparse rewards.
method HyperX uses novel reward bonuses to explore in approximate hyper-state space.
result HyperX meta-learns better task-exploration and adapts more successfully to new tasks.
MxML combines multiple meta-learners to improve few-shot classification.
problem Few-shot classification performance degrades when a new task is out of the training distribution.
method Train an ensemble of meta-learners (MxML) with mixing parameters optimized by a weight prediction network (WPN).
result MxML significantly outperforms state-of-the-art meta-learners and their naive ensemble.
Meta-learning performance depends on train-validation split type.
problem Understanding the importance of train-validation split in meta-learning.
method Theoretical and experimental study comparing train-val and train-train methods.
result Train-train method can achieve strictly better excess loss in realizable cases.
Proposes efficient user cold start recommendation via meta parameter partition.
problem User cold start in recommendation systems.
method Divides model parameters into fixed and adaptive parts, learning them separately offline and online.
result Significant improvement in AUC (2.48% absolute improvement).
Meta-learning reduces training overhead for communication systems.
problem Inefficiency in machine learning due to frequent retraining when system configuration changes.
method Meta-learning selects a suitable inductive bias from related tasks, reducing training data and time requirements.
result Meta-learning can reduce training overhead for communication systems.
Meta-trained optimizers improve model robustness to image corruptions.
problem Robustness of deep learning models to input noise.
method Meta-training a learned optimizer to produce robust models.
result Meta-trained optimizers improve model robustness to Gaussian noise.
CosML combines domain-specific meta-learners for cross-domain few-shot classification.
problem Generalizing to unseen domains while meta-learning on multiple seen domains.
method CosML trains domain-specific meta-learners and combines their meta-parameters in the parameter space.
result CosML outperforms state-of-the-art methods and achieves strong cross-domain generalization.
Meta-learning algorithms prepare quantum Gibbs states efficiently for NISQ devices.
problem Efficiently preparing quantum Gibbs states for NISQ devices.
method Meta-Variational Quantum Thermalizer (Meta-VQT) and Neural Network Meta-VQT (NN-Meta VQT) algorithms.
result Meta-learned parameters significantly outperform random initializations in optimization tasks.
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during …
MetaGenRL learns a general objective function from diverse agents.
problem Generalizing to new environments in reinforcement learning.
method MetaGenRL distills experiences from many agents into a low-complexity neural objective function.
result MetaGenRL can generalize to new environments and outperforms human-engineered algorithms.
Meta-learning improved by using information theory to prioritize data-driven adaptation.
problem Challenges in meta-learning due to the need for mutually-exclusive tasks.
method Designing a meta-regularization objective using information theory.
result Successfully uses data from non-mutually-exclusive tasks to efficiently adapt to novel tasks.
Meta-trained LSTM Meta-Learners learn tasks faster and differently than DL and RL systems.
problem Understanding the learning dynamics of meta-trained LSTM Meta-Learners compared to traditional DL and RL systems.
method Comparative analysis of learning trajectories on three structured tasks.
result Meta-trained LSTM Meta-Learners learn all task structure concurrently, unlike sample-inefficient DL and RL systems.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
problem Adapting models to unseen tasks efficiently and accurately.
method Black-box, metric-based, layered, and Bayesian approaches.
result Meta-learning enhances model generalization and adaptation to unseen tasks.
MOCA enables meta-learning without task segmentation for online learning.
problem Meta-learning without task segmentation for online learning.
method MOCA combines meta-learning with online changepoint analysis.
result MOCA enables efficient meta-learning in time-varying tasks.
Improved stability and generalization for blackbox learned optimizers.
problem Stability and generalization issues in blackbox learned optimizers.
method Investigation using dynamical systems, modifications to optimizer architecture and meta-training procedure.
result Improved stability and generalization of learned optimizers.
Meta-learning improves DNN generalization on standard supervised learning.
problem Improving deep neural networks' generalization without adding more parameters.
method MLTP simulates meta-training by considering a batch of samples as a task, optimizing for both current and new tasks.
result MLTP consistently improves DNN generalization across various sizes and datasets.
Meta-Curvature improves model generalization and adaptation.
problem Enhancing model generalization and adaptation speed.
method Learning to transform gradients to achieve better generalization performance.
result Substantial improvement over previous MAML variants and state-of-the-art methods.
Unified meta-learning framework from supervised learning.
problem Difficulty in comparing and evaluating meta-learning approaches.
method Treating meta-learning as supervised learning, reducing algorithms to supervised learning instances.
result Unified framework and improved model performance on few-shot learning.
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is un…
New method learns robust meta-representations for fast task adaptation.
problem Transferability of meta-representations in fast adaptation.
method Decoupled encoder-decoder approach with contrastive objective.
result Meta-representations improve downstream performance and noise robustness.
Improves memory efficiency for meta-learning with large images.
problem High memory usage in meta-learning for few-shot classification.
method LITE: episodic training scheme that decomposes task gradients and back-propagates only a random subset of images.
result Achieves state-of-the-art accuracy on real-world and challenging benchmarks.
Meta-RL learns shared and task-specific information for quick adaptation.
problem Data inefficiency and limited generalization in deep RL.
method Task embedding and shared policy learned via SGD meta-learner.
result 3 to 4 times higher returns on novel tasks compared to baselines.
DataRater learns which data points are most valuable for training models.
problem Training model efficiency depends on high-quality training data.
method Meta-learning to estimate the value of data points for training.
result Meta-learning improves compute efficiency by filtering data effectively.
TaskNorm improves meta-learning performance by rethinking batch normalization.
problem Challenges in batch normalization for meta-learning with deep networks.
method Developed TaskNorm, a novel approach to batch normalization for meta-learning.
result TaskNorm consistently improves meta-learning performance across various datasets and meta-learning approaches.
Meta-dropout learns to perturb training examples for better generalization.
problem Achieving good generalization in unseen test examples.
method Meta-learning a noise generator to perturb latent features of training examples.
result Meta-dropout significantly improves generalization performance on few-shot classification datasets.
New MAML variant prioritizes hardest tasks, improving robustness.
problem Meta-learning's focus on average performance, ignoring worst-case.
method Reformulate MAML to minimize max loss over observed tasks.
result Task-robust model performs well across various task distributions.