Related papers: Embedding Space Interpolation Beyond Mini-Batch, B…

Mixup is a popular data augmentation method, with many variants subsequently proposed. These methods mainly create new examples via convex combination of random data pairs and their corresponding one-hot labels. However, most of them adhere…

When multiple measures are collected repeatedly over time, redundancy typically exists among responses. The envelope method was recently proposed to reduce the dimension of responses without loss of information in regression with…

In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indicating classes to which instances do not belong, rather than…

Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. Despite extensive research, task interference remains a major…

Subpopulation shift exists widely in many real-world applications, which refers to the training and test distributions that contain the same subpopulation groups but with different subpopulation proportions. Ignoring subpopulation shifts…

Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout strategies have…

To address the issues of MixUp and its variants (e.g., Manifold MixUp) in image classification tasks-namely, their neglect of mixing within the same class (intra-class mixup) and their inadequacy in enhancing intra-class cohesion through…

Spatial multiplexing (SM) gains in multiple input multiple output (MIMO) cellular networks are limited when used in combination with ultra-dense small cell networks. This limitation is due to large spatial correlation among channel pairs.…

Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit…

Embedding models trained separately on similar data often produce representations that encode stable information but are not directly interchangeable. This lack of interoperability raises challenges in several practical applications, such…

Data augmentation in time series forecasting plays a crucial role in enhancing model performance by introducing variability while maintaining the underlying temporal patterns. However, time series data offers fewer augmentation strategies…

Concept blending is a promising yet underexplored area in generative models. While recent approaches, such as embedding mixing and latent modification based on structural sketches, have been proposed, they often suffer from incompatible…

Multidimensional scaling (MDS) is the act of embedding proximity information about a set of $n$ objects in $d$-dimensional Euclidean space. As originally conceived by the psychometric community, MDS was concerned with embedding a fixed set…

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from…

Supervised manifold learning methods for data classification map data samples residing in a high-dimensional ambient space to a lower-dimensional domain in a structure-preserving way, while enhancing the separation between different classes…

Convolutional neural networks for visual recognition require large amounts of training samples and usually benefit from data augmentation. This paper proposes PatchMix, a data augmentation method that creates new samples by composing…

In recent years, the embedding approach for solving switched optimal control problems has been developed in a series of papers. However, the embedding approach, which advantageously converts the hybrid optimal control problem to a classical…

In mesh-based numerical simulations, the interpolation of mesh-defined functions across different meshes is a critical task, and achieving high-precision interpolation is of great significance for improving the computational efficiency and…

The core of the general recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by…

Choosing a suitable deep learning architecture for multimodal data fusion is a challenging task, as it requires the effective integration and processing of diverse data types, each with distinct structures and characteristics. In this…