Related papers: Meta-learning of textual representations

Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize continually in an efficient, effective, and scalable way is…

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this…

Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations. Adaptation is done on a per-task basis, and retraining is needed…

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task. In audio/speech signal processing, a wide range of…

This paper presents an experimental comparison among four Automated Machine Learning (AutoML) methods for recommending the best classification algorithm for a given input dataset. Three of these methods are based on Evolutionary Algorithms…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

Multimodal learning, which aims to understand and analyze information from multiple modalities, has achieved substantial progress in the supervised regime in recent years. However, the heavy dependence on data paired with expensive human…

The AutoSpeech challenge calls for automated machine learning (AutoML) solutions to automate the process of applying machine learning to speech processing tasks. These tasks, which cover a large variety of domains, will be shown to the…

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

Model selection is a critical step in time series forecasting, traditionally requiring extensive performance evaluations across various datasets. Meta-learning approaches aim to automate this process, but they typically depend on…

Demonstration selection is a practical bottleneck in in-context learning (ICL): under a tight prompt budget, accuracy can change substantially depending on which few-shot examples are included, yet selection must remain cheap enough to run…

Since we can leverage a large amount of unlabeled data without any human supervision to train a model and transfer the knowledge to target tasks, self-supervised learning is a de-facto component for the recent success of deep learning in…

Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data to learn useful semantic representations. These pretext tasks are created solely using the input features,…

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic…

Despite the fast progress in training specialized models for various tasks, learning a single general model that works well for many tasks is still challenging for computer vision. Here we introduce multi-task self-training (MuST), which…

Meta-learning is a general approach to equip machine learning models with the ability to handle few-shot scenarios when dealing with many tasks. Most existing meta-learning methods work based on the assumption that all tasks are of equal…

Motivated by the progress made by large language models (LLMs), we introduce the framework of verbalized machine learning (VML). In contrast to conventional machine learning (ML) models that are typically optimized over a continuous…

Multimodal meta-learning is a recent problem that extends conventional few-shot meta-learning by generalizing its setup to diverse multimodal task distributions. This setup makes a step towards mimicking how humans make use of a diverse set…

In recent years, significant progress has been made in scene text recognition by data-driven methods. However, due to the scarcity of annotated real-world data, the training of these methods predominantly relies on synthetic data. The…

Given a graph learning task, such as link prediction, on a new graph, how can we select the best method as well as its hyperparameters (collectively called a model) without having to train or evaluate any model on the new graph? Model…