Related papers: Improving Representational Continuity via Continue…
This work identifies a simple pre-training mechanism that leads to representations exhibiting better continual and transfer learning. This mechanism -- the repeated resetting of weights in the last layer, which we nickname "zapping" -- was…
Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…
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 introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and…
Language models (LMs) trained on vast quantities of unlabelled data have greatly advanced the field of natural language processing (NLP). In this study, we re-visit the widely accepted notion in NLP that continued pre-training LMs on…
In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorithms can improve performance on future tasks, their…
Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to meet continuously emerging requirements without expensive retraining. MCIT faces two major obstacles: catastrophic forgetting (where old…
Deep Neural Network (DNN) has achieved great success on datasets of closed class set. However, new classes, like new categories of social media topics, are continuously added to the real world, making it necessary to incrementally learn.…
Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task…
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretraining, highlighting that it is itself subject to catastrophic…
Neural language models deployed in real-world applications must continually adapt to new tasks and domains without forgetting previously acquired knowledge. This work presents a comparative empirical study of catastrophic forgetting…
Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. In both supervised and unsupervised CL, we…
Incremental Learning (IL) has been a long-standing problem in both vision and Natural Language Processing (NLP) communities. In recent years, as Pre-trained Language Models (PLMs) have achieved remarkable progress in various NLP downstream…
Continual learning (CL) aims to incrementally learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. Most CL works focus on tackling catastrophic forgetting under a learning-from-scratch…
Task-incremental continual learning refers to continually training a model in a sequence of tasks while overcoming the problem of catastrophic forgetting (CF). The issue arrives for the reason that the learned representations are forgotten…
Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of neural networks. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is…
Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to…
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…
Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In…
Sequential training from task to task is becoming one of the major objects in deep learning applications such as continual learning and transfer learning. Nevertheless, it remains unclear under what conditions the trained model's…