arXiv research

Paper tackles online adaptation to changing label distributions.

ELSA efficiently adapts to label shift without post-prediction calibrations.

Paper proposes a method to adapt classifiers using complementary labels instead of true labels.

RLSbench benchmarks domain adaptation under label proportion shifts, revealing widespread failures and proposing a two-step meta-algorithm.

A new method for adapting to label shifts using class probability matching.

EnMDAP aligns conditional distributions for multi-source domain adaptation using pseudolabels.

Adaptive sampling detects local concept drift with limited labels.

PAS method improves UDA by progressively refining subspaces for reliable pseudo-labels.

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in practice: 1) only limited labeled samples are available due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noises (e.g., mi…

Framework for domain adaptation using pseudo-labels from unlabeled data.

Algorithm adapts to shifting domains with minimal label queries.

Paper tackles backwards-compatible data adaptation for confounded covariate and label shifts.

Unsupervised Domain Adaptation (DA) is used to automatize the task of labeling data: an unlabeled dataset (target) is annotated using a labeled dataset (source) from a related domain. We cast domain adaptation as the problem of finding stable labels for target examples. A new definition of label stability is proposed, …

OSAMD adapts online to changing distributions with limited labels.

AdapTable adapts tabular models to shifts without source data, improving HELOC performance.

New algorithm learns from partial labels in general scenarios.

New approach improves domain adaptation with label shift assumptions.

Paper proposes a new method to aggregate multiple sources with different label distributions.

Clarinet uses complementary labels to train classifiers with less source data.

NLE embeds labels for domain adaptation with neural networks.

Domain Adaptation in 6G wireless networks: When is it green?

This work tackles robust multi-source domain adaptation under label shift.

Improves domain adaptation by aligning source and target distributions and mitigating noisy labels.

New method reduces label and data shifts between domains using optimal transport.

Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision sa…

New method uses limited labeled data and multiple starts to adapt models across domains.

Study improves domain adaptation with limited labeled data.

Proposes a new method for handling domain shift in samples with biases in both covariates and labels.

Proposes a label propagation framework for domain adaptation.

Often domain adaptation is performed using a discriminator (domain classifier) to learn domain-invariant feature representations so that a classifier trained on labeled source data will generalize well to unlabeled target data. A line of research stemming from semi-supervised learning uses pseudo labeling to directly g…

Approach for biosensor condition detection using domain adaptation.

Improved segmentation model adaptation for new domains.

In this paper we propose a domain adaptation algorithm designed for graph domains. Given a source graph with many labeled nodes and a target graph with few or no labeled nodes, we aim to estimate the target labels by making use of the similarity between the characteristics of the variation of the label functions on the…

Paper tackles dynamic label shift in online learning, achieving optimal performance.

CAT improves domain adaptation for fault diagnosis by calibrating teacher network predictions.

TTLSA adapts models to label shifts across domains with nuisance factors.

New method removes pseudo-label bias for unsupervised domain adaptation.

A new method for online multi-label stream classification.

Study shows algorithms benefit from limited target data with many source domains.

We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using $K$-means with …

Domain adaptation is an important technique to alleviate performance degradation caused by domain shift, e.g., when training and test data come from different domains. Most existing deep adaptation methods focus on reducing domain shift by matching marginal feature distributions through deep transformations on the inpu…

APLC-XLNet improves XMTC by clustering labels and reducing computational time.

Proposes a framework to improve domain adaptation without labeled data.

Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of labeled data in practice. The existing methods have succeeded by reducing the differen…

Annotating large unlabeled datasets can be a major bottleneck for machine learning applications. We introduce a scheme for inferring labels of unlabeled data at a fraction of the cost of labeling the entire dataset. Our scheme, bounded expectation of label assignment (BELA), greedily queries an oracle (or human labeler…

Proposes a regularization method for unsupervised domain adaptation that aligns predictions with target data's top singular vectors.

TASFAR adapts regression models without labeled source data.

Optimal transport aligns source and target distributions for domain adaptation.