arXiv research

A new meta-meta classification method tackles few-shot learning tasks.

Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.

Gradient-based meta-RL fails with incorrect task distributions, leading to instability and poor performance.

Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal rep…

Meta-learning overfits both model and base learner; meta-augmentation helps.

In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward. In this respect, we develop a novel meta reinforcement learning framework called Hyper-Meta RL(HMRL), for sparse reward RL problems. It is consist…

M3PO improves model-based meta-RL with theoretical guarantees.

Meta learning can adapt fast but is vulnerable to adversarial attacks.

Paper tackles offline meta-reinforcement learning with a new algorithm.

Bayesian MAML outperforms MAML in meta learning tasks with theoretical guarantees.

Modified Meta-TS for linear contextual bandits reduces regret.

Meta-learning algorithm improves AI efficiency by teaching itself.

Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…

Self-referential meta learning avoids explicit optimization by modifying itself.

F-PACOH improves meta-learners' reliability in uncertain regions.

Meta-learning, or learning to learn, is a machine learning approach that utilizes prior learning experiences to expedite the learning process on unseen tasks. As a data-driven approach, meta-learning requires meta-features that represent the primary learning tasks or datasets, and are estimated traditonally as engineer…

Conditional meta-learning improves meta-learning performance in diverse task environments.

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but i…

G-Meta learns graph meta-learning from local subgraphs.

Guarantees for tuning step size using meta-gradient descent.

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…

BOML unifies meta-learning methods into a common bilevel optimization framework.

Meta Omnium benchmarks few-shot learning across diverse vision tasks.

New symmetries improve meta-reinforcement learning's generalization.

New method improves meta-reinforcement learning efficiency.

Meta learning works well with overparameterized models, a phenomenon called 'benign overfitting'.

Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In this paper, we argue that the inter-meta-task relationships should be exploited …

Meta-learning improves feature extraction for few-shot tasks.

VSML unifies meta learning concepts and enables simple backpropagation.

New method improves meta-learning performance by task-specific initialization.

A concise review of recent few-shot meta-learning methods.

Meta-learning bound uses conditional mutual information.

New meta-learning framework for minimizing simple regret in bandits.

Meta-learning balances task-specific modeling and optimization complexity.

Unified framework improves meta-learning generalization bounds.

This paper bounds meta-generalization gap using information theory.

In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few…

Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks …

Meta-learning is increasingly used to support the recommendation of machine learning algorithms and their configurations. Such recommendations are made based on meta-data, consisting of performance evaluations of algorithms on prior datasets, as well as characterizations of these datasets. These characterizations, also…

learn2learn simplifies meta-learning research by providing a library and standardized interfaces.

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space. Such algorithms work well in tasks with relatively slight difference. However, when the task distribution becomes wider, it would be quite inefficient to directly…

A new meta-learning framework that assigns weights to source tasks based on target samples.

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with non…

Several multi-target regression methods were devel-oped in the last years aiming at improving predictive performanceby exploring inter-target correlation within the problem. However, none of these methods outperforms the others for all problems. This motivates the development of automatic approachesto recommend the mos…

Meta-ticket finds optimal sparse subnetworks for few-shot learning in randomly initialized neural networks.

CosML combines domain-specific meta-learners for cross-domain few-shot classification.

Study OOD generalization in meta-reinforcement learning using information theory.

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…