CaMU：在深度模型遗忘中解耦因果效应
CaMU: Disentangling Causal Effects in Deep Model Unlearning
AI总结：
针对现有机器遗忘方法易因遗忘与剩余数据交织导致剩余性能下降或遗忘信息复现的问题，该研究提出因果机器遗忘框架CaMU，通过干预剩余数据信息解耦因果效应，实现遗忘数据影响消除与剩余信息保留的平衡，首次从因果视角为深度模型遗忘提供新方案。
摘要：
机器遗忘要求移除遗忘数据的信息，同时保留剩余数据的必要信息。尽管该领域近期取得了进展，但现有方法主要关注移除遗忘数据的效果，未考虑这一过程可能对剩余数据信息造成的负面影响，导致数据移除后模型性能显著下降。虽然部分方法尝试在移除后修复剩余数据的性能，但修复过程中遗忘信息也可能重新出现。这一问题源于遗忘数据与剩余数据的复杂交织。若未能充分区分两类数据对模型的影响，现有算法要么存在遗忘数据移除不充分的风险，要么会造成剩余数据中宝贵信息的不必要损失。为解决这一缺陷，本研究对遗忘任务开展了因果分析，并提出了名为Causal Machine Unlearning（因果机器遗忘，CaMU）的新型框架。该框架对剩余数据的信息施加干预，以解耦遗忘数据与剩余数据之间的因果效应。随后CaMU消除与遗忘数据相关的因果影响，同时保留剩余数据的因果关联。在多个数据集和模型上开展的综合实验结果表明，CaMU提升了剩余数据上的性能，且有效降低了遗忘数据的影响。值得注意的是，本研究首次从因果关系新视角解读深度模型遗忘任务，并提供了基于因果分析的解决方案，为深度模型遗忘的未来研究开辟了新的可能。
英文摘要：
Machine unlearning requires removing the information of forgetting data while keeping the necessary information of remaining data. Despite recent advancements in this area, existing methodologies mainly focus on the effect of removing forgetting data without considering the negative impact this can have on the information of the remaining data, resulting in significant performance degradation after data removal. Although some methods try to repair the performance of remaining data after removal, the forgotten information can also return after repair. Such an issue is due to the intricate intertwining of the forgetting and remaining data. Without adequately differentiating the influence of these two kinds of data on the model, existing algorithms take the risk of either inadequate removal of the forgetting data or unnecessary loss of valuable information from the remaining data. To address this shortcoming, the present study undertakes a causal analysis of the unlearning and introduces a novel framework termed Causal Machine Unlearning (CaMU). This framework adds intervention on the information of remaining data to disentangle the causal effects between forgetting data and remaining data. Then CaMU eliminates the causal impact associated with forgetting data while concurrently preserving the causal relevance of the remaining data. Comprehensive empirical results on various datasets and models suggest that CaMU enhances performance on the remaining data and effectively minimizes the influences of forgetting data. Notably, this work is the first to interpret deep model unlearning tasks from a new perspective of causality and provide a solution based on causal analysis, which opens up new possibilities for future research in deep model unlearning.
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。
