Related papers: Forget Less by Learning Together through Concept C…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

Data privacy and silos are nontrivial and greatly challenging in many real-world applications. Federated learning is a decentralized approach to training models across multiple local clients without the exchange of raw data from client…

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…

Continual learning (CL) aims to learn new tasks while retaining past knowledge, addressing the challenge of forgetting during task adaptation. Rehearsal-based methods, which replay previous samples, effectively mitigate forgetting. However,…

Continual learning empowers models to learn from a continuous stream of data while preserving previously acquired knowledge, effectively addressing the challenge of catastrophic forgetting. In this study, we propose a new approach that…

Federated and Continual Learning have emerged as potential paradigms for the robust and privacy-aware use of Deep Learning in dynamic environments. However, Client Drift and Catastrophic Forgetting are fundamental obstacles to guaranteeing…

Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what…

We introduce Compartmentalized Diffusion Models (CDM), a method to train different diffusion models (or prompts) on distinct data sources and arbitrarily compose them at inference time. The individual models can be trained in isolation, at…

Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks…

Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…

As Web technology continues to develop, it has become increasingly common to use data stored on different clients. At the same time, federated learning has received widespread attention due to its ability to protect data privacy when let…

A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks when learning new tasks. This problem has been widely…

We introduce a novel continual learning method based on multifidelity deep neural networks. This method learns the correlation between the output of previously trained models and the desired output of the model on the current training…

Neural networks can achieve excellent results in a wide variety of applications. However, when they attempt to sequentially learn, they tend to learn the new task while catastrophically forgetting previous ones. We propose a model that…

To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples…

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual…

The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance…

The training of deep learning models in seizure prediction requires large amounts of Electroencephalogram (EEG) data. However, acquiring sufficient labeled EEG data is difficult due to annotation costs and privacy constraints. Federated…

General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments. Conventional learning algorithms for neural networks, however, suffer from catastrophic forgetting (CF), i.e., previously…

Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large…