Adversarial Batch Representation Augmentation for Batch Correction in High-Content Cellular Screening
High-Content Screening routinely generates massive volumes of cell painting images for phenotypic profiling. However, technical variations across experimental executions inevitably induce biological batch (bio-batch) effects. These cause covariate shifts and degrade the generalization of deep learning models on unseen data. Existing batch correction methods typically rely on additional prior knowledge (e.g., treatment or cell culture information) or struggle to generalize to unseen bio-batches. In this work, we frame bio-batch mitigation as a Domain Generalization (DG) problem and propose Adversarial Batch Representation Augmentation (ABRA). ABRA explicitly models batch-wise statistical fluctuations by parameterizing feature statistics as structured uncertainties. Through a min-max optimization framework, it actively synthesizes worst-case bio-batch perturbations in the representation space, guided by a strict angular geometric margin to preserve fine-grained class discriminability. To prevent representation collapse during this adversarial exploration, we introduce a synergistic distribution alignment objective. Extensive evaluations on the large-scale RxRx1 and RxRx1-WILDS benchmarks demonstrate that ABRA establishes a new state-of-the-art for siRNA perturbation classification.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationSimilar Papers 제목 키워드 기반
Concurrent Adversarial Learning for Large-Batch Training
Large-batch training has become a commonly used technique when training neural networks with a large number of GPU/TPU processors. As batch size increases, stochastic optimizers tend to converge to sharp local minima, le…
Data AugmentationGPUscMEDAL for the interpretable analysis of single-cell transcriptomics data with batch effect visualization using a deep mixed effects autoencoder
scRNA-seq data has the potential to provide new insights into cellular heterogeneity and data acquisition; however, a major challenge is unraveling confounding from technical and biological batch effects. Existing batch …
Virtual Augmentation Supported Contrastive Learning of Sentence Representations
Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natural language processing where no general…
Contrastive LearningData AugmentationRepresentation LearningSentenceContrastive Learning with Adversarial Examples
Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext lea…
Contrastive LearningSelf-Supervised LearningscSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SSL methods applied to single-cell data, w…
BenchmarkingData AugmentationData IntegrationSelf-Supervised Learning