TLXML:通过影响函数进行元学习的任务级解释
TLXML: Task-Level Explanation of Meta-Learning via Influence Functions
AI总结:
TLXML通过影响函数为元学习提供任务级解释,量化元训练任务对模型行为的贡献,提升元学习的可解释性和可信度。
摘要:
元学习使模型能够通过利用先前经验快速适应新任务,但其适应机制仍保持模糊,尤其是过去训练任务如何影响未来预测的问题。我们介绍了TLXML(元学习的任务级解释),一种将影响函数扩展到元学习设置的新框架,使能够对适应和推理进行任务级解释。通过将影响函数重新公式化为双层优化,TLXML量化了每个元训练任务对适应模型行为的贡献。为了确保可扩展性,我们提出了一种基于高斯-牛顿的近似方法,将计算复杂度从O(pq²)显著降低到O(pq),其中p和q分别表示模型和元参数。结果表明,TLXML能够有效按对下游性能的影响对训练任务进行排序,提供简洁直观的解释,与用户级抽象一致。这项工作为可解释和可信的元学习系统提供了关键一步。
英文摘要:
Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially regarding how past training tasks influence future predictions. We introduce TLXML (Task-Level eXplanation of Meta-Learning), a novel framework that extends influence functions to meta-learning settings and provides task-level explanations of adaptation and inference. By reformulating influence functions for the bi-level structure of meta-learning, we quantify the contribution of each meta-training task to the adapted model's behaviour. To ensure scalability, we propose a Gauss-Newton-based approximation that significantly reduces computational complexity from $O(pq^2)$ to $O(pq)$, where $p$ and $q$ denote the numbers of model and meta parameters, respectively. Moreover, we propose generalized influence functions defined using pseudo-inverse Hessian, which are applicable even when the loss landscape has flat directions. Results demonstrate that TLXML effectively ranks training tasks by their influence on downstream performance, offering concise, intuitive explanations aligned with user-level abstraction. This work provides a critical step toward interpretable and trustworthy meta-learning systems.
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。