Related papers: Efficient Feature Transformations for Discriminati…

Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven…

Feature Transformation (FT) crafts new features from original ones via mathematical operations to enhance dataset expressiveness for downstream models. However, existing FT methods exhibit critical limitations: discrete search struggles…

Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization problem, converting…

This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared…

Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift…

We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations. Our approach is based on learning a set of global and task-specific…

Recently, evolutionary multitasking (EMT) has been successfully used in the field of high-dimensional classification. However, the generation of multiple tasks in the existing EMT-based feature selection (FS) methods is relatively simple,…

Online continual learning for image classification is crucial for models to adapt to new data while retaining knowledge of previously learned tasks. This capability is essential to address real-world challenges involving dynamic…

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Pre-trained representation is one of the key elements in the success of modern deep learning. However, existing works on continual learning methods have mostly focused on learning models incrementally from scratch. In this paper, we explore…

This study addresses the actual behavior of the credit-card fraud detection environment where financial transactions containing sensitive data must not be amassed in an enormous amount to conduct learning. We introduce a new adaptive…

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and…

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the…

As sounds carry rich information, environmental sound classification (ESC) is crucial for numerous applications such as rare wild animals detection. However, our world constantly changes, asking ESC models to adapt to new sounds…

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Traditional model-free feature selection methods treat each feature independently while disregarding the interrelationships among features, which leads to relatively poor performance compared with the model-aware methods. To address this…

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…

Despite the massive success of fine-tuning Pre-trained Language Models (PLMs), they remain susceptible to out-of-distribution input. Dataset cartography is a simple yet effective dual-model approach that improves the robustness of…