Related papers: Oops, I Sampled it Again: Reinterpreting Confidenc…
Large Language Models exhibit powerful few-shot in-context learning (ICL) capabilities, but the performance is highly sensitive to provided examples. Recent research has focused on retrieving corresponding examples for each input query, not…
Few-shot learning is often motivated by the ability of humans to learn new tasks from few examples. However, standard few-shot classification benchmarks assume that the representation is learned on a limited amount of base class data,…
In most machine learning tasks, we evaluate a model $M$ on a given data population $S$ by measuring a population-level metric $F(S;M)$. Examples of such evaluation metric $F$ include precision/recall for (binary) recognition, the F1 score…
This paper presents a simple, effective, and cost-efficient strategy to improve LLM performance by scaling test-time compute. Our strategy builds upon the repeated-sampling-then-voting framework, with a novel twist: incorporating multiple…
Standard random-effects meta-analysis methods perform poorly when applied to few studies only. Such settings however are commonly encountered in practice. It is unclear, whether or to what extent small-sample-size behaviour can be improved…
In this work we introduce a novel approach, based on sampling, for finding assignments that are likely to be solutions to stochastic constraint satisfaction problems and constraint optimisation problems. Our approach reduces the size of the…
Labelling data is a major practical bottleneck in training and testing classifiers. Given a collection of unlabelled data points, we address how to select which subset to label to best estimate test metrics such as accuracy, $F_1$ score or…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
Existing approaches to few-shot learning in NLP rely on large language models (LLMs) and/or fine-tuning of these to generalise on out-of-distribution data. In this work, we propose a novel few-shot learning approach based on soft-label…
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on…
Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance. However, the class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.…
Few-shot learning (FSL) methods typically assume clean support sets with accurately labeled samples when training on novel classes. This assumption can often be unrealistic: support sets, no matter how small, can still include mislabeled…
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying…
Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model…
Experience replay is a key component in reinforcement learning for stabilizing learning and improving sample efficiency. Its typical implementation samples transitions with replacement from a replay buffer. In contrast, in supervised…
The current standard for confidence interval construction in the context of a possibly misspecified model is to use an interval based on the sandwich estimate of variance. These intervals provide asymptotically correct coverage, but…
Contrastive Language-Image Pre-training (CLIP) has shown powerful zero-shot learning performance. Few-shot learning aims to further enhance the transfer capability of CLIP by giving few images in each class, aka 'few shots'. Most existing…
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To…
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…
Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and rely heavily on a…