DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation 事件

DISCO: Mitigating Bias in Deep Learning with Conditional Distance Correlation arXiv:2506.11653v3 Announce Type: replace Abstract: Dataset bias often leads deep learning models to exploit spurious correlations instead of task-relevant signals. We introduce the Standard Anti-Causal Model (SAM), a unifying causal framework that characterizes bias mechanisms and yields a conditional independence criterion for causal stability. Building on this theory, we propose DISCO$_m$ and sDISCO, efficient and