Related papers: MetaXT: Meta Cross-Task Transfer between Disparate…

Performance of neural network models relies on the availability of large datasets with minimal levels of uncertainty. Transfer Learning (TL) models have been proposed to resolve the issue of small dataset size by letting the model train on…

Scarcity of parallel sentence pairs is a major challenge for training high quality neural machine translation (NMT) models in bilingually low-resource scenarios, as NMT is data-hungry. Multi-task learning is an elegant approach to inject…

Reading comprehension is a challenging task in natural language processing and requires a set of skills to be solved. While current approaches focus on solving the task as a whole, in this paper, we propose to use a neural network `skill'…

Foundation models have emerged as a powerful tool for many AI problems. Despite the tremendous success of foundation models, effective adaptation to new tasks, particularly those with limited labels, remains an open question and lacks…

We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as…

Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph…

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success,…

This paper proposes a novelty approach to mitigate the negative transfer problem. In the field of machine learning, the common strategy is to apply the Single-Task Learning approach in order to train a supervised model to solve a specific…

Many few-shot learning approaches have been designed under the meta-learning framework, which learns from a variety of learning tasks and generalizes to new tasks. These meta-learning approaches achieve the expected performance in the…

In medical image analysis, transfer learning is a powerful method for deep neural networks (DNNs) to generalize well on limited medical data. Prior efforts have focused on developing pre-training algorithms on domains such as lung…

Deploying natural language processing (NLP) models on mobile platforms requires models that can adapt across diverse applications while remaining efficient in memory and computation. We investigate pre-finetuning strategies to enhance the…

Language style transfer has attracted more and more attention in the past few years. Recent researches focus on improving neural models targeting at transferring from one style to the other with labeled data. However, transferring across…

Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within…

Natural Language Processing (NLP) has seen remarkable advances in recent years, particularly with the emergence of Large Language Models that have achieved unprecedented performance across many tasks. However, these developments have mainly…

Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approaches treat different source tasks equally, ignoring the…

Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered…

Multi-task problem solving has been shown to improve the accuracy of the individual tasks, which is an important feature for robots, as they have a limited resource. However, when the number of labels for each task is not equal, namely…

We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. META-MT provides a new approach to make NMT models easily adaptable to many target domains with the minimal amount of…

Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training. Towards this goal, this…

In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information…