# TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning

arXiv: https://arxiv.org/abs/2604.02183 · HTML: https://mlsanity.com/paper/2604.02183/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 25 of 25)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Reliability of CKA as a Similarity Measure in Deep Learning](https://mlsanity.com/paper/2210.16156/) (2022)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback](https://mlsanity.com/paper/2111.02036/) (2021)
- [Membership Inference Attacks Against Recommender Systems](https://mlsanity.com/paper/2109.08045/) (2021)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [A Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2207.12515/) (2022)
- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [Multi-View Graph Convolutional Network for Multimedia Recommendation](https://mlsanity.com/paper/2308.03588/) (2023)
- [Selective and Collaborative Influence Function for Efficient Recommendation Unlearning](https://mlsanity.com/paper/2304.10199/) (2023)
- [Recommendation Unlearning via Influence Function](https://mlsanity.com/paper/2307.02147/) (2023)
- [MultiDelete for Multimodal Machine Unlearning](https://mlsanity.com/paper/2311.12047/) (2023)
- [A Comprehensive Survey on Multimodal Recommender Systems: Taxonomy, Evaluation, and Future Directions](https://mlsanity.com/paper/2302.04473/) (2023)
- [Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier](https://mlsanity.com/paper/2408.09212/) (2024)
- [A Survey of Real-World Recommender Systems: Challenges, Constraints, and Industrial Perspectives](https://mlsanity.com/paper/2509.06002/) (2025)
- [CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence](https://mlsanity.com/paper/2408.14393/) (2024)
- [Modality-Balanced Learning for Multimedia Recommendation](https://mlsanity.com/paper/2408.06360/) (2024)
- [A Survey on Multimodal Recommender Systems: Recent Advances and Future Directions](https://mlsanity.com/paper/2502.15711/) (2025)
- [MONET: Modality-Embracing Graph Convolutional Network and Target-Aware Attention for Multimedia Recommendation](https://mlsanity.com/paper/2312.09511/) (2023)
- [Towards Federated Domain Unlearning: Verification Methodologies and Challenges](https://mlsanity.com/paper/2406.03078/) (2024)

## Abstract (arXiv)

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 textitranking behavior, textitmodality branches, and textitmodel 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 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.