Related papers: MEMENTO: Leveraging Web as a Learning Signal for L…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

Named Entity Recognition (NER) is a machine learning task that traditionally relies on supervised learning and annotated data. Acquiring such data is often a challenge, particularly in specialized fields like medical, legal, and financial…

As an algorithmic framework for learning to learn, meta-learning provides a promising solution for few-shot text classification. However, most existing research fail to give enough attention to class labels. Traditional basic framework…

The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently learning and deploying the correct behaviors exemplified in each…

Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in…

Recent advances in semi-supervised learning (SSL) demonstrate that a combination of consistency regularization and pseudo-labeling can effectively improve image classification accuracy in the low-data regime. Compared to classification,…

Categorizing documents into a given label hierarchy is intuitively appealing due to the ubiquity of hierarchical topic structures in massive text corpora. Although related studies have achieved satisfying performance in fully supervised…

Medical professionals frequently work in a data constrained setting to provide insights across a unique demographic. A few medical observations, for instance, informs the diagnosis and treatment of a patient. This suggests a unique setting…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…

Active Learning (AL) is a powerful tool for learning with less labeled data, in particular, for specialized domains, like legal documents, where unlabeled data is abundant, but the annotation requires domain expertise and is thus expensive.…

Supervised machine learning has become the cornerstone of today's data-driven society, increasing the need for labeled data. However, the process of acquiring labels is often expensive and tedious. One possible remedy is to use active…

Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at…

Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest. One is typically required to collect a large mount of data (i.e., base…

Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…

In stream-based active learning, the learning procedure typically has access to a stream of unlabeled data instances and must decide for each instance whether to label it and use it for training or to discard it. There are numerous active…

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…

Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…