Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization performance. However, our experiments reveal an unexpected result: there is negative knowledge transfer between tasks, affecting generalization performance. To explain this phenomenon, we conduct Structural Causal Models (SCMs) for causal analysis. Our investigation uncovers the presence of spurious correlations between task-specific causal factors and labels in meta-learning. Furthermore, the confounding factors differ across different batches. We refer to these confounding factors as "Task Confounders". Based on these findings, we propose a plug-and-play Meta-learning Causal Representation Learner (MetaCRL) to eliminate task confounders. It encodes decoupled generating factors from multiple tasks and utilizes an invariant-based bi-level optimization mechanism to ensure their causality for meta-learning. Extensive experiments on various benchmark datasets demonstrate that our work achieves state-of-the-art (SOTA) performance.

翻译：元学习通过从多种任务中学习知识，实现对新任务的快速泛化。直观上认为随着训练进程的推进，模型将获得更丰富的知识，从而带来更好的泛化性能。然而，我们的实验揭示了一个意外结果：任务间存在负向知识迁移，影响了泛化性能。为解释这一现象，我们采用结构因果模型（SCMs）进行因果分析。研究发现，元学习中存在任务特异性因果因子与标签间的伪相关性。此外，不同批次间的混淆因子存在差异。我们将这些混淆因子称为“任务混淆因子”。基于这些发现，我们提出了一种即插即用的元学习因果表征学习器（MetaCRL）以消除任务混淆因子。该方法从多任务中编码解耦的生成因子，并利用基于不变性的双层优化机制确保其对于元学习的因果性。在多种基准数据集上的大量实验表明，我们的工作实现了最先进的性能。