相关论文: La-MAML: Look-ahead Meta Learning for Continual Le…

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic…

Model-agnostic meta-learning (MAML) formulates meta-learning as a bilevel optimization problem, where the inner level solves each subtask based on a shared prior, while the outer level searches for the optimal shared prior by optimizing its…

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…

This article reviews meta-learning also known as learning-to-learn which seeks rapid and accurate model adaptation to unseen tasks with applications in highly automated AI, few-shot learning, natural language processing and robotics. Unlike…

Software refactoring is the process of changing the structure of software without any alteration in its behavior and functionality. Presuming it is carried out in appropriate opportunities, refactoring enhances software quality…

Neural networks are known to suffer from catastrophic forgetting when trained on sequential datasets. While there have been numerous attempts to solve this problem in large-scale supervised classification, little has been done to overcome…

Optimization-based meta-learning aims to learn an initialization so that a new unseen task can be learned within a few gradient updates. Model Agnostic Meta-Learning (MAML) is a benchmark algorithm comprising two optimization loops. The…

Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning. It uses gradient descent to learn commonalities between various tasks, enabling the model to learn the meta-initialization of…

Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks observed in the past. There are however other desirable properties of a CL system,…

Continual learning is the ability to acquire new knowledge without forgetting the previously learned one, assuming no further access to past training data. Neural network approximators trained with gradient descent are known to fail in this…

Despite the superior empirical success of deep meta-learning, theoretical understanding of overparameterized meta-learning is still limited. This paper studies the generalization of a widely used meta-learning approach, Model-Agnostic…

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

Meta-learning offers a principled framework leveraging \emph{task-invariant} priors from related tasks, with which \emph{task-specific} models can be fine-tuned on downstream tasks, even with limited data records. Gradient-based…

Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a…

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Meta-learning, which pursues an effective initialization model, has emerged as a promising approach to handling unseen tasks. However, a limitation remains to be evident when a meta-learner tries to encompass a wide range of task…

In the realm of recommender systems, the ubiquitous adoption of deep neural networks has emerged as a dominant paradigm for modeling diverse business objectives. As user bases continue to expand, the necessity of personalization and…

Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs). However, adapting these pre-trained models to dynamic data distributions and various tasks efficiently remains a…