Forget-MI unlearns unimodal and joint embeddings of patient data in a multimodal chest X-ray model, reducing membership inference attack success by 0.202 while preserving only part of the original test performance.
Motives for withdrawal of participation in biobanking and participants’ willingness to allow linkages of their data.European Journal of Human Genetics, 30:1–11, 11 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings
Forget-MI unlearns unimodal and joint embeddings of patient data in a multimodal chest X-ray model, reducing membership inference attack success by 0.202 while preserving only part of the original test performance.