Search Results for author:
Found 18 papers, 5 papers with code
Distributionally Generative Augmentation for Fair Facial Attribute Classification
This work proposes a novel, generation-based two-stage framework to train a fair FAC model on biased data without additional annotation.
Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
To bridge this gap between optimization and OOD generalization, we study the effect of sharpness on how a model tolerates data change in domain shift which is usually captured by "robustness" in generalization.
A Survey on Evaluation of Out-of-Distribution Generalization
In closing, we propose several promising directions for future research in OOD evaluation.
Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications
Machine learning algorithms minimizing average risk are susceptible to distributional shifts.
Understanding Prompt Tuning for V-L Models Through the Lens of Neural Collapse
It is found that NC optimality of text-to-image representations shows a positive correlation with downstream generalizability, which is more severe under class imbalance settings.
Meta Adaptive Task Sampling for Few-Domain Generalization
Moreover, we propose a Meta Adaptive Task Sampling (MATS) procedure to differentiate base tasks according to their semantic and domain-shift similarity to the novel task.
Rethinking the Evaluation Protocol of Domain Generalization
This paper examines the risks of test data information leakage from two aspects of the current evaluation protocol: supervised pretraining on ImageNet and oracle model selection.
Exploring and Exploiting Data Heterogeneity in Recommendation
In this work, we focus on exploring two representative categories of heterogeneity in recommendation data that is the heterogeneity of prediction mechanism and covariate distribution and propose an algorithm that explores the heterogeneity through a bilevel clustering method.
Predictive Heterogeneity: Measures and Applications
As an intrinsic and fundamental property of big data, data heterogeneity exists in a variety of real-world applications, such as precision medicine, autonomous driving, financial applications, etc.
Enhancing Distributional Stability among Sub-populations
shifts in prediction mechanisms ($Y|X$-shifts).
Towards Domain Generalization in Object Detection
Despite the striking performance achieved by modern detectors when training and test data are sampled from the same or similar distribution, the generalization ability of detectors under unknown distribution shifts remains hardly studied.
Integrated Latent Heterogeneity and Invariance Learning in Kernel Space
The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.
Kernelized Heterogeneous Risk Minimization
The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.
Towards Out-Of-Distribution Generalization: A Survey
This paper represents the first comprehensive, systematic review of OOD generalization, encompassing a spectrum of aspects from problem definition, methodological development, and evaluation procedures, to the implications and future directions of the field.
Distributionally Robust Learning with Stable Adversarial Training
In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with the target.
Heterogeneous Risk Minimization
In this paper, we propose Heterogeneous Risk Minimization (HRM) framework to achieve joint learning of latent heterogeneity among the data and invariant relationship, which leads to stable prediction despite distributional shifts.
Stable Adversarial Learning under Distributional Shifts
Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data.
Triple Generative Adversarial Networks
It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN).
