相关论文: A Unified Contrastive-Generative Framework for Tim…

The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences. Due to the data sparsity and noise issues in sequences, a new self-supervised learning…

Self-supervised learning (SSL) has had great success in both computer vision. Most of the current mainstream computer vision SSL frameworks are based on Siamese network architecture. These approaches often rely on cleverly crafted loss…

As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to…

The success of contrastive learning depends on the construction and utilization of high-quality positive pairs. However, current methods face critical limitations on two fronts: on the construction side, both handcrafted and generative…

Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification…

While state-of-the-art contrastive Self-Supervised Learning (SSL) models produce results competitive with their supervised counterparts, they lack the ability to infer latent variables. In contrast, prescribed latent variable (LV) models…

Cross-silo federated learning (CFL) enables organizations (e.g., hospitals or banks) to collaboratively train artificial intelligence (AI) models while preserving data privacy by keeping data local. While prior work has primarily addressed…

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. As one of the most popular graph-based SSL approaches, the recently proposed Graph…

Multivariate Time-Series (MTS) clustering is crucial for signal processing and data analysis. Although deep learning approaches, particularly those leveraging Contrastive Learning (CL), are prominent for MTS representation, existing…

We introduce UniGen, a unified multimodal large language model (MLLM) capable of image understanding and generation. We study the full training pipeline of UniGen from a data-centric perspective, including multi-stage pre-training,…

Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Given the abundance of unlabeled Satellite Image Time Series (SITS) and the scarcity of labeled data, contrastive self-supervised pretraining emerges as a natural tool to leverage this vast quantity of unlabeled data. However, designing…

Time series self-supervised learning (SSL) aims to exploit unlabeled data for pre-training to mitigate the reliance on labels. Despite the great success in recent years, there is limited discussion on the potential noise in the time series,…

Semi-supervised learning (SSL) is a promising approach for training deep classification models using labeled and unlabeled datasets. However, existing SSL methods rely on a large unlabeled dataset, which may not always be available in many…

While text-to-image generative models can synthesize diverse and faithful content, subject variation across multiple generations limits their application to long-form content generation. Existing approaches require time-consuming…

Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unlabeled data and reducing reliance on costly manual…

Contrastive Learning (CL), a leading paradigm in Self-Supervised Learning (SSL), typically relies on pairs of data views generated through augmentation. While multiple augmentations per instance (more than two) improve generalization in…

Recently, various contrastive learning techniques have been developed to categorize time series data and exhibit promising performance. A general paradigm is to utilize appropriate augmentations and construct feasible positive samples such…