Related papers: Drift-Aware Multi-Memory Model for Imbalanced Data…

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the…

Diffusion models, known for their tremendous ability to generate novel and high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy risks. Recent approaches for memory mitigation…

Real-world datasets are inherently heterogeneous, yet how per-class structural differences and sampling imbalance shape the training dynamics of diffusion models-and potentially exacerbate disparities-remains poorly understood. While models…

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Neural networks trained with class-imbalanced data are known to perform poorly on minor classes of scarce training data. Several recent works attribute this to over-fitting to minor classes. In this paper, we provide a novel explanation of…

Continuous learning from an immense volume of data streams becomes exceptionally critical in the internet era. However, data streams often do not conform to the same distribution over time, leading to a phenomenon called concept drift.…

Detecting concept drift in high-speed data streams remains challenging, particularly when models must operate on unlabeled data and avoid false alarms caused by benign shifts. While disagreement-based uncertainty has shown promise in neural…

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,…

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Automated driving object detection has always been a challenging task in computer vision due to environmental uncertainties. These uncertainties include significant differences in object sizes and encountering the class unseen. It may…

In the pursuit of autonomous learning systems, the foundational assumption of stationarity, the premise that data distributions and model behaviors remain constant, is fundamentally untenable. Historically, the research community has…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions,…

Deep artificial neural networks famously struggle to learn from non-stationary streams of data. Without dedicated mitigation strategies, continual learning is associated with continuous forgetting of previous tasks and a progressive loss of…

In recent years, we have seen a handful of work on inference algorithms over non-stationary data streams. Given their flexibility, Bayesian non-parametric models are a good candidate for these scenarios. However, reliable streaming…

Class imbalance exists in many classification problems, and since the data is designed for accuracy, imbalance in data classes can lead to classification challenges with a few classes having higher misclassification costs. The Backblaze…

Machine learning-based intrusion detection requires complex models to capture patterns in high-dimensional, noisy, and class-imbalanced raw network traffic, yet deploying such models remains impractical on resource-constrained devices with…

Recent years have witnessed growing interests in online incremental learning. However, there are three major challenges in this area. The first major difficulty is concept drift, that is, the probability distribution in the streaming data…

Training models on highly unbalanced data is admitted to be a challenging task for machine learning algorithms. Current studies on deep learning mainly focus on data sets with balanced class labels or unbalanced data, but with massive…

In the online continual learning paradigm, agents must learn from a changing distribution while respecting memory and compute constraints. Experience Replay (ER), where a small subset of past data is stored and replayed alongside new data,…