Related papers: DynaTab: Dynamic Feature Ordering as Neural Rewiri…

Tabular data plays a crucial role in various domains but often suffers from missing values, thereby curtailing its potential utility. Traditional imputation techniques frequently yield suboptimal results and impose substantial computational…

Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) has demonstrated that alternatives are possible. The point-wise function DyT…

Despite the prevalence and significance of tabular data across numerous industries and fields, it has been relatively underexplored in the realm of deep learning. Even today, neural networks are often overshadowed by techniques such as…

Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP),…

Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations. As surrogate task, we jointly address ordering of visual data in the spatial and temporal…

In this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear time-invariant dynamical systems, the topic of damping factor identification…

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular…

In many real-world regression tasks, the data distribution is heavily skewed, and models learn predominantly from abundant majority samples while failing to predict minority labels accurately. While imbalanced classification has been…

Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting…

Accurate prediction of protein-ligand binding affinities is an essential challenge in structure-based drug design. Despite recent advances in data-driven methods for affinity prediction, their accuracy is still limited, partially because…

Tabular data represent one of the most prevalent data formats in applied machine learning, largely because they accommodate a broad spectrum of real-world problems. Existing literature has studied many of the shortcomings of neural…

Diabetic Retinopathy (DR) progresses as a continuous and irreversible deterioration of the retina, following a well-defined clinical trajectory from mild to severe stages. However, most existing ordinal regression approaches model DR…

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…

Dynamical density functional theory (DDFT) is a powerful variational framework to study the nonequilibrium properties of colloids by only considering a time-dependent one-body number density. Despite the large number of recent successes,…

Understanding the causal relationships between data variables can provide crucial insights into the construction of tabular datasets. Most existing causality learning methods typically focus on applying a single identifiable causal model,…

Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However,…

Long-tailed visual recognition is challenging not only due to class imbalance but also because of varying classification difficulty across categories. Simply reweighting classes by frequency often overlooks those that are intrinsically hard…

Goal-conditioned dynamic manipulation is inherently challenging due to complex system dynamics and stringent task constraints, particularly in deformable object scenarios characterized by high degrees of freedom and underactuation. Prior…

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. The first contribution of the paper is to extend…

To deal with various datasets over different complexity, this paper presents an self-adaptive learning model that combines the proposed Dynamic Connected Neural Decision Networks (DNDN) and a new pruning method--Dynamic Soft Pruning (DSP).…