Related papers: Zero-Shot Task Transfer
Humans can naturally learn to execute a new task by seeing it performed by other individuals once, and then reproduce it in a variety of configurations. Endowing robots with this ability of imitating humans from third person is a very…
Online meta-learning has recently emerged as a marriage between batch meta-learning and online learning, for achieving the capability of quick adaptation on new tasks in a lifelong manner. However, most existing approaches focus on the…
Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages…
The importance of building semantic parsers which can be applied to new domains and generate programs unseen at training has long been acknowledged, and datasets testing out-of-domain performance are becoming increasingly available.…
The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent years. Contrary to conventional approaches to AI where tasks are solved from scratch using a fixed learning algorithm, meta-learning aims to…
Long text summarization, gradually being essential for efficiently processing large volumes of information, stays challenging for Large Language Models (LLMs) such as GPT and LLaMA families because of the insufficient open-sourced training…
Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The…
Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specific tasks by pulling…
The ability to transfer knowledge from prior experiences to novel tasks stands as a pivotal capability of intelligent agents, including both humans and computational models. This principle forms the basis of transfer learning, where large…
Pre-training a deep neural network on the ImageNet dataset is a common practice for training deep learning models, and generally yields improved performance and faster training times. The technique of pre-training on one task and then…
Modern meta-learning approaches for image classification rely on increasingly deep networks to achieve state-of-the-art performance, making batch normalization an essential component of meta-learning pipelines. However, the hierarchical…
Classical deep neural networks are limited in their ability to learn from emerging streams of training data. When trained sequentially on new or evolving tasks, their performance degrades sharply, making them inappropriate in real-world use…
Zero-shot learning (ZSL) is a challenging problem that aims to recognize the target categories without seen data, where semantic information is leveraged to transfer knowledge from some source classes. Although ZSL has made great progress…
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in…
Recent work has shown that language models (LMs) trained with multi-task \textit{instructional learning} (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning. MTIL illustrates…
We present a meta-learning based generative model for zero-shot learning (ZSL) towards a challenging setting when the number of training examples from each \emph{seen} class is very few. This setup contrasts with the conventional ZSL…
In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically…
We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single task setting to the meta-learning multiple task setting to…
Albeit the universal representational power of pre-trained language models, adapting them onto a specific NLP task still requires a considerably large amount of labeled data. Effective task fine-tuning meets challenges when only a few…
Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be…