Related papers: FreRA: A Frequency-Refined Augmentation for Contra…

What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…

Diffusion models have achieved remarkable success in generative modeling, yet how to effectively adapt large pretrained models to new tasks remains challenging. We revisit the reconstruction behavior of diffusion models during denoising to…

Time series forecasting is crucial in many fields, yet current deep learning models struggle with noise, data sparsity, and capturing complex multi-scale patterns. This paper presents MFF-FTNet, a novel framework addressing these challenges…

Sequential recommender systems (SRS) are designed to predict users' future behaviors based on their historical interaction data. Recent research has increasingly utilized contrastive learning (CL) to leverage unsupervised signals to…

Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a…

Federated learning (FL) remains highly vulnerable to adaptive backdoor attacks that preserve stealth by closely imitating benign update statistics. Existing defenses predominantly rely on anomaly detection in parameter or gradient space,…

Self-Supervised learning aims to eliminate the need for expensive annotation in graph representation learning, where graph contrastive learning (GCL) is trained with the self-supervision signals containing data-data pairs. These data-data…

Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short-cyclic effects, which can lead…

Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…

Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the…

The lack of labeled data is a key challenge for learning useful representation from time series data. However, an unsupervised representation framework that is capable of producing high quality representations could be of great value. It is…

Training GANs under limited data often leads to discriminator overfitting and memorization issues, causing divergent training. Existing approaches mitigate the overfitting by employing data augmentations, model regularization, or attention…

Self-Supervised Learning (SSL) enables us to pre-train foundation models without costly labeled data. Among SSL methods, Contrastive Learning (CL) methods are better at obtaining accurate semantic representations in noise interference.…

Data augmentation (DA) has become a de facto solution to expand training data size for deep learning. With the proliferation of deep models for time series analysis, various time series DA techniques are proposed in the literature, e.g.,…

Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL…

In this article we introduce a broad family of adaptive, linear time-frequency representations termed superposition frames, and show that they admit desirable fast overlap-add reconstruction properties akin to standard short-time Fourier…

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…

Contrastive learning has gained popularity and pushes state-of-the-art performance across numerous large-scale benchmarks. In contrastive learning, the contrastive loss function plays a pivotal role in discerning similarities between…

While Low-Rank Adaptation (LoRA) has proven beneficial for efficiently fine-tuning large models, LoRA fine-tuned text-to-image diffusion models lack diversity in the generated images, as the model tends to copy data from the observed…

Contrastive learning has shown effectiveness in improving sequential recommendation models. However, existing methods still face challenges in generating high-quality contrastive pairs: they either rely on random perturbations that corrupt…