Related papers: SubTab: Subsetting Features of Tabular Data for Se…

Despite tremendous progress over the past decade, deep learning methods generally fall short of human-level systematic generalization. It has been argued that explicitly capturing the underlying structure of data should allow connectionist…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Tabular data learning has extensive applications in deep learning but its existing embedding techniques are limited in numerical and categorical features such as the inability to capture complex relationships and engineering. This paper…

Context of data points, which is usually defined as the other data points in a data set, has been found to play important roles in data representation and classification. In this paper, we study the problem of using context of a data point…

Tabular data is the foundation of the information age and has been extensively studied. Recent studies show that neural-based models are effective in learning contextual representation for tabular data. The learning of an effective…

Self-supervised learning (SSL) has been incorporated into many state-of-the-art models in various domains, where SSL defines pretext tasks based on unlabeled datasets to learn contextualized and robust representations. Recently, SSL has…

Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because…

Domain adaptation (DA) is a representation learning methodology that transfers knowledge from a label-sufficient source domain to a label-scarce target domain. While most of early methods are focused on unsupervised DA (UDA), several…

Deep neural networks often under-perform on tabular data due to their sensitivity to irrelevant features and a spectral bias toward smooth, low-frequency functions. These limitations hinder their ability to capture the sharp, high-frequency…

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their…

Synthesizing high-quality tabular data is an important topic in many data science tasks, ranging from dataset augmentation to privacy protection. However, developing expressive generative models for tabular data is challenging due to its…

Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data, and multi-source domain adaptation (MSDA) is very attractive for real world applications. By learning…

Unsupervised feature learning often finds low-dimensional embeddings that capture the structure of complex data. For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may…

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic…

Autoregressive and Masked Transformers are incredibly effective as generative models and classifiers. While these models are most prevalent in NLP, they also exhibit strong performance in other domains, such as vision. This work contributes…

Unsupervised Domain Adaptation (UDA) addresses the problem of performance degradation due to domain shift between training and testing sets, which is common in computer vision applications. Most existing UDA approaches are based on…

Estimating the parameters of a model describing a set of observations using a neural network is in general solved in a supervised way. In cases when we do not have access to the model's true parameters this approach can not be applied.…

Tabular data is the most commonly used form of data in industry. Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data. DNN models using…

Self-supervised tasks have been utilized to build useful representations that can be used in downstream tasks when the annotation is unavailable. In this paper, we introduce a self-supervised video representation learning method based on…

Deep learning methods are successfully used in applications pertaining to ubiquitous computing, health, and well-being. Specifically, the area of human activity recognition (HAR) is primarily transformed by the convolutional and recurrent…