Hacking Task Confounder in Meta-Learning

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. The code is provided in https: //github. com/WangJingyao07/MetaCRL.

Authors

• Jingyao Wang
• Yi Ren Zhejiang Univerisity
• Zeen Song
• Jianqi Zhang
• Changwen Zheng Institute of Software, Chinese Academy of Sciences University of the Chinese Academy of Sciences
• Wenwen Qiang Science & Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences

Keywords

• Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning
• Machine Learning: ML: Causality
• Machine Learning: ML: Few-shot learning
• Machine Learning: ML: Meta-learning