Addressing Missing Sources with Adversarial Support-Matching
When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate or non-deliberate censorship, and other problems during data collection and curation, the labeled training set might exhibit a systematic shortage of data for certain groups. We investigate a scenario in which the absence of certain data is linked to the second level of a two-level hierarchy in the data. Inspired by the idea of protected groups from algorithmic fairness, we refer to the partitions carved by this second level as "subgroups"; we refer to combinations of subgroups and classes, or leaves of the hierarchy, as "sources". To characterize the problem, we introduce the concept of classes with incomplete subgroup support. The representational bias in the training set can give rise to spurious correlations between the classes and the subgroups which render standard classification models ungeneralizable to unseen sources. To overcome this bias, we make use of an additional, diverse but unlabeled dataset, called the "deployment set", to learn a representation that is invariant to subgroup. This is done by adversarially matching the support of the training and deployment sets in representation space. In order to learn the desired invariance, it is paramount that the sets of samples observed by the discriminator are balanced by class; this is easily achieved for the training set, but requires using semi-supervised clustering for the deployment set. We demonstrate the effectiveness of our method with experiments on several datasets and variants of the problem.
Code (1)
Tasks
FairnessSimilar Papers 제목 키워드 기반
Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
Missing data are present in most real world problems and need careful handling to preserve the prediction accuracy and statistical consistency in the downstream analysis. As the gold standard of handling missing data, mu…
Generative Adversarial NetworkImputationBridging the Gap in Missing Modalities: Leveraging Knowledge Distillation and Style Matching for Brain Tumor Segmentation
Accurate and reliable brain tumor segmentation, particularly when dealing with missing modalities, remains a critical challenge in medical image analysis. Previous studies have not fully resolved the challenges of tumor …
Brain Tumor SegmentationKnowledge DistillationSemi-Supervised Learning with Adversarially Missing Label Information
We address the problem of semi-supervised learning in an adversarial setting. Instead of assuming that labels are missing at random, we analyze a less favorable scenario where the label information can be missing partial…
Generalization Boundsparameter estimationID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction
Performing recognition tasks using latent fingerprint samples is often challenging for automated identification systems due to poor quality, distortion, and partially missing information from the input samples. We propos…
Generative Adversarial NetworkUFed-GAN: A Secure Federated Learning Framework with Constrained Computation and Unlabeled Data
To satisfy the broad applications and insatiable hunger for deploying low latency multimedia data classification and data privacy in a cloud-based setting, federated learning (FL) has emerged as an important learning par…
Federated LearningGenerative Adversarial Network