Picture for Nan Lu

Nan Lu

A General Framework for Learning under Corruption: Label Noise, Attribute Noise, and Beyond

Add code
Jul 17, 2023
Viaarxiv icon

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Add code
May 24, 2023
Viaarxiv icon

Learning from Multiple Unlabeled Datasets with Partial Risk Regularization

Add code
Jul 04, 2022
Figure 1 for Learning from Multiple Unlabeled Datasets with Partial Risk Regularization
Figure 2 for Learning from Multiple Unlabeled Datasets with Partial Risk Regularization
Figure 3 for Learning from Multiple Unlabeled Datasets with Partial Risk Regularization
Figure 4 for Learning from Multiple Unlabeled Datasets with Partial Risk Regularization
Viaarxiv icon

Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients

Add code
Apr 07, 2022
Figure 1 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 2 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 3 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Figure 4 for Federated Learning from Only Unlabeled Data with Class-Conditional-Sharing Clients
Viaarxiv icon

Rethinking Importance Weighting for Transfer Learning

Add code
Dec 19, 2021
Figure 1 for Rethinking Importance Weighting for Transfer Learning
Figure 2 for Rethinking Importance Weighting for Transfer Learning
Figure 3 for Rethinking Importance Weighting for Transfer Learning
Figure 4 for Rethinking Importance Weighting for Transfer Learning
Viaarxiv icon

Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification

Add code
Feb 01, 2021
Figure 1 for Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Figure 2 for Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Figure 3 for Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Figure 4 for Binary Classification from Multiple Unlabeled Datasets via Surrogate Set Classification
Viaarxiv icon

Pointwise Binary Classification with Pairwise Confidence Comparisons

Add code
Oct 05, 2020
Figure 1 for Pointwise Binary Classification with Pairwise Confidence Comparisons
Figure 2 for Pointwise Binary Classification with Pairwise Confidence Comparisons
Figure 3 for Pointwise Binary Classification with Pairwise Confidence Comparisons
Viaarxiv icon

A One-step Approach to Covariate Shift Adaptation

Add code
Jul 08, 2020
Figure 1 for A One-step Approach to Covariate Shift Adaptation
Figure 2 for A One-step Approach to Covariate Shift Adaptation
Figure 3 for A One-step Approach to Covariate Shift Adaptation
Viaarxiv icon

Rethinking Importance Weighting for Deep Learning under Distribution Shift

Add code
Jun 08, 2020
Figure 1 for Rethinking Importance Weighting for Deep Learning under Distribution Shift
Figure 2 for Rethinking Importance Weighting for Deep Learning under Distribution Shift
Figure 3 for Rethinking Importance Weighting for Deep Learning under Distribution Shift
Figure 4 for Rethinking Importance Weighting for Deep Learning under Distribution Shift
Viaarxiv icon

Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach

Add code
Oct 20, 2019
Figure 1 for Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
Figure 2 for Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
Figure 3 for Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
Figure 4 for Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
Viaarxiv icon