TRU is a plug-and-play unlearning method for multimodal recommenders that applies ranking fusion, modality scaling, and layer isolation to achieve better retain-forget trade-offs than uniform baselines.
InPro- ceedings of the AAAI Conference on Artificial Intelligence(2021), vol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning
TRU is a plug-and-play unlearning method for multimodal recommenders that applies ranking fusion, modality scaling, and layer isolation to achieve better retain-forget trade-offs than uniform baselines.