Related papers: Scalable Causal Domain Adaptation
Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-driven models on…
Domain generalization aims to learn knowledge invariant across different distributions while semantically meaningful for downstream tasks from multiple source domains, to improve the model's generalization ability on unseen target domains.…
This paper addresses the challenge of fault root cause identification in cloud computing environments. The difficulty arises from complex system structures, dense service coupling, and limited fault information. To solve this problem, an…
Unsupervised domain adaptation without consuming annotation process for unlabeled target data attracts appealing interests in semantic segmentation. However, 1) existing methods neglect that not all semantic representations across domains…
The capacity to transfer knowledge across scientific domains relies on shared organizational principles. However, existing transfer-learning methodologies often fail to bridge radically heterogeneous systems, particularly under severe data…
Time series anomaly detection is a challenging task with a wide range of real-world applications. Due to label sparsity, training a deep anomaly detector often relies on unsupervised approaches. Recent efforts have been devoted to time…
Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher layers in the model, the…
Current approaches which are mainly based on the extraction of low-level relations among individual events are limited by the shortage of publicly available labelled data. Therefore, the resulting models perform poorly when applied to a…
Machine learning algorithms typically assume that the training and test samples come from the same distributions, i.e., in-distribution. However, in open-world scenarios, streaming big data can be Out-Of-Distribution (OOD), rendering these…
A basic assumption of statistical learning theory is that train and test data are drawn from the same underlying distribution. Unfortunately, this assumption doesn't hold in many applications. Instead, ample labeled data might exist in a…
Human activity recognition aims to recognize the activities of daily living by utilizing the sensors on different body parts. However, when the labeled data from a certain body position (i.e. target domain) is missing, how to leverage the…
Causal discovery methods can identify valid adjustment sets for causal effect estimation for a pair of target variables, even when the underlying causal graph is unknown. Global causal discovery methods focus on learning the whole causal…
Domain adaptation solves the learning problem in a target domain by leveraging the knowledge in a relevant source domain. While remarkable advances have been made, almost all existing domain adaptation methods heavily require large amounts…
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.…
Transfer learning aims at transferring knowledge from a well-labeled domain to a similar but different domain with limited or no labels. Unfortunately, existing learning-based methods often involve intensive model selection and…
Causal Temporal Representation Learning (Ctrl) methods aim to identify the temporal causal dynamics of complex nonstationary temporal sequences. Despite the success of existing Ctrl methods, they require either directly observing the domain…
Unsupervised domain adaptation leverages abundant labeled data from various source domains to generalize onto unlabeled target data. Prior research has primarily focused on learning domain-invariant features across the source and target…
We propose associative domain adaptation, a novel technique for end-to-end domain adaptation with neural networks, the task of inferring class labels for an unlabeled target domain based on the statistical properties of a labeled source…
Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…
Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…