arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.07281cs.LG
收藏

监督对比块解纠缠

Supervised Contrastive Block Disentanglement

Center for Data Science, New York University(纽约大学数据科学中心);Genentech(基因泰克公司);Stanford University(斯坦福大学)
Taro Makino, Ji Won Park, Natasa Tagasovska, Takamasa Kudo, Paula Coelho, Jan-Christian Huetter, Heming Yao, Burkhard Hoeckendorf, Ana Carolina Leote, Stephen R… 展开作者

Taro Makino, Ji Won Park, Natasa Tagasovska, Takamasa Kudo, Paula Coelho, Jan-Christian Huetter, Heming Yao, Burkhard Hoeckendorf, Ana Carolina Leote, Stephen Ra, David Richmond, Kyunghyun Cho, Aviv Regev, Romain Lopez

AI总结:

针对现实数据集因不同实验条件引入虚假相关性的问题,提出监督对比块解纠缠(SCBD)算法,通过学习两个独立嵌入分别表示目标现象与虚假相关性,强化对环境变量的不变性,在领域泛化和批次校正任务上表现优异。

摘要:

现实世界的数据集通常整合了不同实验条件下收集的数据,这虽能生成更大的数据集,但也引入了虚假相关性,导致难以对目标现象建模。我们通过学习两个嵌入来独立表示目标现象和虚假相关性,其中表示目标现象的嵌入与目标变量$y$相关且对环境变量$e$具有不变性,而表示虚假相关性的嵌入与$e$相关。在现实世界数据集上实现对$e$的不变性颇具挑战。我们的主要贡献是提出一种名为监督对比块解纠缠(SCBD)的算法,能有效强化这种不变性。该算法纯基于监督对比学习,在现实世界数据上的表现优于现有方法。我们在两个具有挑战性的问题上对SCBD进行了实证验证:一是领域泛化问题,在合成数据集和Camelyon17-WILDS上均取得了优异性能;二是批次校正问题,将SCBD应用于2600万张光学池筛选图像的单细胞扰动建模,以保留生物信号并消除孔间批次效应。

英文摘要:

Real-world datasets often combine data collected under different experimental conditions. This yields larger datasets, but also introduces spurious correlations that make it difficult to model the phenomena of interest. We address this by learning two embeddings to independently represent the phenomena of interest and the spurious correlations. The embedding representing the phenomena of interest is correlated with the target variable $y$, and is invariant to the environment variable $e$. In contrast, the embedding representing the spurious correlations is correlated with $e$. The invariance to $e$ is difficult to achieve on real-world datasets. Our primary contribution is an algorithm called Supervised Contrastive Block Disentanglement (SCBD) that effectively enforces this invariance. It is based purely on Supervised Contrastive Learning, and applies to real-world data better than existing approaches. We empirically validate SCBD on two challenging problems. The first problem is domain generalization, where we achieve strong performance on a synthetic dataset, as well as on Camelyon17-WILDS. We introduce a single hyperparameter $α$ to control the degree of invariance to $e$. When we increase $α$ to strengthen the degree of invariance, out-of-distribution performance improves at the expense of in-distribution performance. The second problem is batch correction, in which we apply SCBD to preserve biological signal and remove inter-well batch effects when modeling single-cell perturbations from 26 million Optical Pooled Screening images.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑