相关论文: Gradient Correlation Subspace Learning against Cat…

Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some work has also been done to transfer…

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Continual learning (CL) empowers AI systems to progressively acquire knowledge from non-stationary data streams. However, catastrophic forgetting remains a critical challenge. In this work, we identify attention drift in Vision Transformers…

Federated learning (FL) has attracted growing attention via data-private collaborative training on decentralized clients. However, most existing methods unrealistically assume object classes of the overall framework are fixed over time. It…

We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when learning multiple tasks sequentially. This…

This paper considers incremental few-shot learning, which requires a model to continually recognize new categories with only a few examples provided. Our study shows that existing methods severely suffer from catastrophic forgetting, a…

Continual learning (CL) is an approach to address catastrophic forgetting, which refers to forgetting previously learned knowledge by neural networks when trained on new tasks or data distributions. The adversarial robustness has decomposed…

Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards…

We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly.…

Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without forgetting previously learned information. Although…

Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation (EWC), a…

Deep learning models often suffer from forgetting previously learned information when trained on new data. This problem is exacerbated in federated learning (FL), where the data is distributed and can change independently for each user.…

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods…

When a computational system continuously learns from an ever-changing environment, it rapidly forgets its past experiences. This phenomenon is called catastrophic forgetting. While a line of studies has been proposed with respect to…

Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all…

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Large language models exhibit remarkable performance across diverse tasks through pre-training and fine-tuning paradigms. However, continual fine-tuning on sequential tasks induces catastrophic forgetting, where newly acquired knowledge…

Catastrophic forgetting - the tendency of neural networks to forget previously learned data when learning new information - remains a central challenge in continual learning. In this work, we adopt a behavioral approach, observing a…

Deep Neural Networks (DNNs) suffer from a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. This phenomenon, known as catastrophic forgetting, prevents DNNs from…