Related papers: Adaptive Shortcut Debiasing for Online Continual L…

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where…

In the realm of high-frequency data streams, achieving real-time learning within varying memory constraints is paramount. This paper presents Ferret, a comprehensive framework designed to enhance online accuracy of Online Continual Learning…

Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite…

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…

Biased attributes, spuriously correlated with target labels in a dataset, can problematically lead to neural networks that learn improper shortcuts for classifications and limit their capabilities for out-of-distribution (OOD)…

Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in leveraging previously acquired knowledge to learn new tasks…

This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive…

Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP…

The development of artificial intelligence demands that models incrementally update knowledge by Continual Learning (CL) to adapt to open-world environments. To meet privacy and security requirements, Continual Unlearning (CU) emerges as an…

Online Continual learning is a challenging learning scenario where the model must learn from a non-stationary stream of data where each sample is seen only once. The main challenge is to incrementally learn while avoiding catastrophic…

Catastrophic forgetting is a significant challenge in online continual learning (OCL), especially for non-stationary data streams that do not have well-defined task boundaries. This challenge is exacerbated by the memory constraints and…

Deep-learning models can extract a rich assortment of features from data. Which features a model uses depends not only on \emph{predictivity} -- how reliably a feature indicates training-set labels -- but also on \emph{availability} -- how…

We study online learning in adversarial nonstationary environments. Since the future can be very different from the past, a critical challenge is to gracefully forget the history while new data comes in. To formalize this intuition, we…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring classes, making it prone to catastrophic forgetting and high false-positive rates (FPR). Extending CLIP to MLCIL is…

Memory decay makes it harder for the human brain to recognize visual objects and retain details. Consequently, recorded brain signals become weaker, uncertain, and contain poor visual context over time. This paper presents one of the first…

In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization…