Related papers: Retrofit: Continual Learning with Controlled Forge…
Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.…
Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well…
Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP…
In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved…
Large language models (LLMs) and multimodal models (MMs) have exhibited impressive capabilities in various domains, particularly in general language understanding and visual reasoning. However, these models, trained on massive data, may not…
Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distribution easily…
Fine-tuning vision-language models (VLMs) such as CLIP often leads to catastrophic forgetting of pretrained knowledge. Prior work primarily aims to mitigate forgetting during adaptation; however, forgetting often remains inevitable during…
With the memory-resource-limited constraints, class-incremental learning (CIL) usually suffers from the "catastrophic forgetting" problem when updating the joint classification model on the arrival of newly added classes. To cope with the…
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed…
Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), models often struggle to balance learning new tasks (plasticity)…
Existing continual learning (CL) research regards catastrophic forgetting (CF) as almost the only challenge. This paper argues for another challenge in class-incremental learning (CIL), which we call cross-task class discrimination…
Continual learning (CL) in large language models (LLMs) is an evolving domain that focuses on developing efficient and sustainable training strategies to adapt models to emerging knowledge and achieve robustness in dynamic environments. Our…
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies…
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and…
Continual learning (CL) studies the problem of learning a sequence of tasks, one at a time, such that the learning of each new task does not lead to the deterioration in performance on the previously seen ones while exploiting previously…
Even in the era of large models, one of the well-known issues in continual learning (CL) is catastrophic forgetting, which is significantly challenging when the continual data stream exhibits a long-tailed distribution, termed as…
As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is introduced to seek to mitigate these risks by removing the influence of undesirable data.…
Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal…
Cybersecurity is increasingly threatened by advanced and persistent attacks. As these attacks are often designed to disable a system (or a critical resource, e.g., a user account) repeatedly, it is crucial for the defender to keep updating…
A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…