The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the data generating distributions remain constant across the environments or alternately, the data "overlaps" across environments to find meaningful invariant features. Consequently, when the "overlap" assumption does not hold, the set of truly invariant features may not be sufficient for optimal prediction performance. Such cases arise naturally in networked settings and hierarchical data-generating models, wherein the IRM performance becomes suboptimal. To mitigate this failure case, we argue for a partial invariance framework. The key idea is to introduce flexibility into the IRM framework by partitioning the environments based on hierarchical differences, while enforcing invariance locally within the partitions. We motivate this framework in classification settings with causal distribution shifts across environments. Our results show the capability of the partial invariant risk minimization to alleviate the trade-off between fairness and risk in certain settings.
翻译:变化风险最小化框架(IRM)旨在从一系列环境中学习解决分配外(OOOD)一般化问题的各种环境的变量特征。基本假设是,产生数据分布的因果组成部分在整个环境中或交替地保持不变,数据“重叠”跨环境以找到有意义的变化性特征。因此,当“重叠”假设不成立时,一套真正变化性特征可能不足以实现最佳预测性能。这类情况自然出现在网络设置和等级数据生成模型中,其中IMM的性能变得不理想。为了减轻这一失败情况,我们主张采用部分差异框架。关键的想法是,根据等级差异对环境进行分割,同时在分区内执行本地差异。我们鼓励这一框架在环境分类环境中采用因果分布的变化。我们的结果表明,部分变化风险最小化能够减轻某些环境的公平与风险之间的权衡。