TRU:面向高效多模态推荐去学习的定向反向更新
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
AI总结:
针对多模态推荐系统中数据删除影响不均匀的问题,提出TRU框架,通过层级化干预实现更高效的去学习,提升保留与遗忘的平衡。
摘要:
多模态推荐系统(MRS)联合建模用户-物品交互图和丰富物品内容,但这种紧密耦合使用户数据难以删除。近似机器去学习提供了一种高效的替代方案,但现有方法主要依赖于模型层面的统一反向更新。本文表明,这一假设与现代MRS不匹配:删除数据的影响并非均匀分布,而是集中在排名行为、模态分支和网络层上。这种非均匀性导致去学习的三个瓶颈:协同图中目标物品的持久性、特征分支间的模态不平衡以及参数空间中的层间敏感性。为解决这一不匹配,本文提出目标反向更新(TRU),一种适用于MRS的即插即用去学习框架。TRU通过模型层级的三个协调干预:排名融合门以抑制残余目标物品影响,分支级模态缩放以保留保留的多模态表示,以及容量感知的层隔离以局部化反向更新到敏感模块。在两个代表性backbone、三个数据集和三种去学习模式上的实验表明,TRU在保留与遗忘的平衡上优于现有近似基线,安全审计进一步证实更深入的遗忘和更接近全重训练的效果。
英文摘要:
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 current MRS unlearning applies reverse updates largely uniformly across model components. We show that this uniform treatment is misaligned with modern MRS: deleted-data influence is distributed unevenly across \textit{ranking behavior}, \textit{modality branches}, and \textit{model modules}. This non-uniformity gives rise to three bottlenecks in MRS unlearning: target-item persistence in the collaborative graph, modality imbalance across feature branches, and concentrated module-level 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 uniform 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 parameter-group selection to localize reverse updates to deletion-sensitive modules. Across two backbones, three datasets, and three unlearning regimes, TRU achieves a stronger retain--forget trade-off than MMRecUn in most settings. In two challenging user-level cases, TRU also attains favorable operating points among all evaluated baselines. Security audits report the lowest MIA BalAcc and a tie for the lowest ASR among approximate methods in both audited settings, while wall-clock trajectories show earlier convergence to favorable retain--forget regions.
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。