Related papers: Unleashing the Power of Graph Data Augmentation on…

Out-of-distribution (OOD) prediction is often approached by restricting models to causal or invariant covariates, avoiding non-causal spurious associations that may be unstable across environments. Despite its theoretical appeal, this…

Adversarial perturbations pose a significant threat to deep learning models. Adversarial Training (AT), the predominant defense method, faces challenges of high computational costs and a degradation in standard performance. While data…

Detectors trained with massive labeled data often exhibit dramatic performance degradation in some particular scenarios with data distribution gap. To alleviate this problem of domain shift, conventional wisdom typically concentrates solely…

Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant existing methods in…

The software outlined in this paper, AitiaExplorer, is an exploratory causal analysis tool which uses unsupervised learning for feature selection in order to expedite causal discovery. In this paper the problem space of causality is briefly…

Machine learning models trained on imbalanced datasets often exhibit intersectional biases-systematic errors arising from the interaction of multiple attributes such as object class and environmental conditions. This paper presents a…

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between…

In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…

Real-world classification problems must contend with domain shift, the (potential) mismatch between the domain where a model is deployed and the domain(s) where the training data was gathered. Methods to handle such problems must specify…

Existing methods for graph out-of-distribution (OOD) generalization primarily rely on empirical studies on synthetic datasets. Such approaches tend to overemphasize the causal relationships between invariant sub-graphs and labels, thereby…

In this paper, we study the problem of unsupervised graph representation learning by harnessing the control properties of dynamical networks defined on graphs. Our approach introduces a novel framework for contrastive learning, a widely…

Data integration is essential across diverse domains, from historical records to biomedical research, facilitating joint statistical inference. A crucial initial step in this process involves merging multiple data sources based on matching…

Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image classification tasks, its application to time-series…

Data augmentation is a major component of many machine learning methods with state-of-the-art performance. Common augmentation strategies work by drawing random samples from a space of transformations. Unfortunately, such sampling…

The application of supervised deep learning methods in digital pathology is limited due to their sensitivity to domain shift. Digital Pathology is an area prone to high variability due to many sources, including the common practice of…

Dealing with distribution shifts is one of the central challenges for modern machine learning. One fundamental situation is the covariate shift, where the input distributions of data change from training to testing stages while the…

Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to task-irrelevant semantics, separability of classes in some latent space, and…