Related papers: Forward-Only Continual Learning

Balancing sensitivity to new tasks and stability for retaining past knowledge is crucial in continual learning (CL). Recently, sharpness-aware minimization has proven effective in transfer learning and has also been adopted in continual…

Current reinforcement learning algorithms train an agent using forward-generated trajectories, which provide little guidance so that the agent can explore as much as possible. While realizing the value of reinforcement learning results from…

Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old data, replay-based…

Modern big-data systems generate massive, heterogeneous, and geographically dispersed streams that are large-scale and privacy-sensitive, making centralization challenging. While federated learning (FL) provides a privacy-enhancing training…

Continual Few-shot Relation Extraction (CFRE) is a practical problem that requires the model to continuously learn novel relations while avoiding forgetting old ones with few labeled training data. The primary challenges are catastrophic…

The ability of neural networks to continuously learn and adapt to new tasks while retaining prior knowledge is crucial for many applications. However, current neural networks tend to forget previously learned tasks when trained on new ones,…

Continual learning is essential for adapting models to new tasks while retaining previously acquired knowledge. While existing approaches predominantly focus on uni-modal data, multi-modal learning offers substantial benefits by utilizing…

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights…

Catastrophic forgetting (CF) happens whenever a neural network overwrites past knowledge while being trained on new tasks. Common techniques to handle CF include regularization of the weights (using, e.g., their importance on past tasks),…

The forward-forward algorithm presents a new method of training neural networks by updating weights during an inference, performing parameter updates for each layer individually. This immediately reduces memory requirements during training…

Deep neural networks are susceptible to adversarial attacks, which can compromise their performance and accuracy. Adversarial Training (AT) has emerged as a popular approach for protecting neural networks against such attacks. However, a…

As machine learning systems increasingly rely on data subject to privacy regulation, selectively unlearning specific information from trained models has become essential. In image classification, this involves removing the influence of…

Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as queries. Conventional forward learning consumes enormous queries…

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates,…

Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mixture-of-Experts (MoE) architectures offer an efficient path to scaling, existing…

Catastrophic forgetting(CF) is a significant challenge in continual learning (CL). In regularization-based approaches to mitigate CF, modifications to important training parameters are penalized in subsequent tasks using an appropriate loss…

Continual learning involves learning from a stream of data without repetition of data points, a scenario that is inherently complex due to distributional shift across tasks. We propose a query-only attention mechanism that discards keys and…

This paper considers continual learning of large-scale pretrained neural machine translation model without accessing the previous training data or introducing model separation. We argue that the widely used regularization-based methods,…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…