Multimodal recommendation systems (MRS) jointly model user-item interaction graphs and rich item content, but this tight coupling makes user data difficult to remove once learned. Approximate machine unlearning offers an efficient alternative to full retraining, yet existing methods for MRS mainly rely on a largely uniform reverse update across the model. We show that this assumption is fundamentally mismatched to modern MRS: deleted-data influence is not uniformly distributed, but concentrated unevenly across \textit{ranking behavior}, \textit{modality branches}, and \textit{network layers}. This non-uniformity gives rise to three bottlenecks in MRS unlearning: target-item persistence in the collaborative graph, modality imbalance across feature branches, and layer-wise sensitivity in the parameter space. To address this mismatch, we propose \textbf{targeted reverse update} (TRU), a plug-and-play unlearning framework for MRS. Instead of applying a blind global reversal, TRU performs three coordinated interventions across the model hierarchy: a ranking fusion gate to suppress residual target-item influence in ranking, branch-wise modality scaling to preserve retained multimodal representations, and capacity-aware layer isolation to localize reverse updates to deletion-sensitive modules. Experiments across two representative backbones, three datasets, and three unlearning regimes show that TRU consistently achieves a better retain-forget trade-off than prior approximate baselines, while security audits further confirm deeper forgetting and behavior closer to a full retraining on the retained data.

翻译：多模态推荐系统（MRS）协同建模用户-物品交互图与丰富的物品内容，但这种紧密耦合使得用户数据一旦被学习便难以移除。近似机器遗忘为完全重训练提供了高效替代方案，然而现有针对MRS的方法主要依赖对模型施加近乎统一的反向更新。本文证明该假设与现代MRS存在根本性失配：被删除数据的影响并非均匀分布，而是不均衡地集中于\textit{排序行为}、\textit{模态分支}和\textit{网络层}。这种非均匀性在MRS遗忘中引发三类瓶颈：协作图中目标物品的持续残留、特征分支间的模态失衡以及参数空间的逐层敏感性。针对这一失配问题，我们提出\textbf{目标反向更新}（TRU），一种即插即用的MRS遗忘框架。TRU不采用盲目的全局反转，而是通过三种协同干预在模型层级进行调控：排序融合门控抑制排序中的目标物品残留影响、分支-wise模态缩放保持保留的多模态表征、以及基于容量的层级隔离将反向更新限定于删除敏感模块。在两种代表性骨干网络、三个数据集及三种遗忘场景下的实验表明，TRU始终能比现有近似基线方法实现更优的保留-遗忘权衡，安全性审计进一步验证其实现了更彻底的遗忘效果，且行为更接近于基于保留数据的完全重训练。