Related papers: FeatNavigator: Automatic Feature Augmentation on T…

Data preparation, also called data wrangling, is considered one of the most expensive and time-consuming steps when performing analytics or building machine learning models. Preparing data typically involves collecting and merging data from…

Training deep learning models and performing hyperparameter tuning can be computationally demanding and time-consuming. Meanwhile, traditional machine learning methods like gradient-boosting algorithms remain the preferred choice for most…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Data augmentations are important in training high-performance 3D object detectors for point clouds. Despite recent efforts on designing new data augmentations, perhaps surprisingly, most state-of-the-art 3D detectors only use a few simple…

Data augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics. In this work, we instead propose to automatically…

Over the last decade, the long-running endeavour to automate high-level processes in machine learning (ML) has risen to mainstream prominence, stimulated by advances in optimisation techniques and their impact on selecting ML…

Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a…

Accurate predictions on tabular data rely on capturing complex, dataset-specific feature interactions. Attention-based methods and graph neural networks, referred to as graph-based tabular deep learning (GTDL), aim to improve predictions by…

In recent years, deep learning models have demonstrated remarkable success in various domains, such as computer vision, natural language processing, and speech recognition. However, the generalization capabilities of these models can be…

Traditional Machine Learning (ML) models like Support Vector Machine, Random Forest, and Logistic Regression are generally preferred for classification tasks on tabular datasets. Tabular data consists of rows and columns corresponding to…

Structural biology has made significant progress in determining membrane proteins, leading to a remarkable increase in the number of available structures in dedicated databases. The inherent complexity of membrane protein structures,…

Multi-label (ML) classification is an actively researched topic currently, which deals with convoluted and overlapping boundaries that arise due to several labels being active for a particular data instance. We propose a classifier capable…

Feature transformation aims to reconstruct the feature space of raw features to enhance the performance of downstream models. However, the exponential growth in the combinations of features and operations poses a challenge, making it…

One of the growing trends in machine learning is the use of data generation techniques, since the performance of machine learning models is dependent on the quantity of the training dataset. However, in many real-world applications,…

Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is…

Building high-quality datasets and labeling query-document relevance are essential yet resource-intensive tasks, requiring detailed guidelines and substantial effort from human annotators. This paper explores the use of small, fine-tuned…

Model-heterogeneous personalized federated learning (MHPFL) enables FL clients to train structurally different personalized models on non-independent and identically distributed (non-IID) local data. Existing MHPFL methods focus on…

Feature missing is a serious problem in many applications, which may lead to low quality of training data and further significantly degrade the learning performance. While feature acquisition usually involves special devices or complex…

Recent development of deep neural networks (DNNs) for tabular learning has largely benefited from the capability of DNNs for automatic feature interaction. However, the heterogeneity nature of tabular features makes such features relatively…

Specializing LLMs in various domain-specific tasks has emerged as a critical step towards achieving high performance. However, the construction and annotation of datasets in specific domains are always very costly. Apart from using superior…