IDSISA：基于影响力蒸馏分片训练的高效机器遗忘方法
IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning
AI 导读
IDSISA（Influence-Distilled SISA）是针对机器遗忘的改进训练方法，用影响力函数将易遗忘样本集中到少数分片，并通过未受影响分片的蒸馏恢复隔离训练损失的效用。
正文 · 原文
Abstract:Machine unlearning removes the influence of specific training examples to comply with privacy regulations. Full retraining gives strong guarantees but is computationally prohibitive at scale; approximate methods are efficient but lack formal guarantees. SISA (Sharded, Isolated, Sliced, and Aggregated training) achieves certified deletion through data sharding and independent retraining, but random partitioning scatters forget requests across most shards, and isolated retraining degrades utility. We introduce IDSISA (Influence-Distilled SISA), which uses influence functions to concentrate forget-prone samples into few shards and distillation from unaffected shards to recover utility lost to isolation. The deletion guarantee inherited from SISA's retraining step remains exact and requires no probabilistic qualification; the distillation-based utility recovery is a separately quantified, empirically bounded approximation ($\epsilon_{\text{cert}} \leq 0.015$ in expectation). We further formalize certification under sequences of repeated deletion requests, where cross-shard distillation can create dependencies between shards; we prove that a closure-based cascading retraining procedure restores the deletion guarantee to the full aggregated model under any deletion sequence. Experiments on ResNet-18/CIFAR-10, ResNet-18/CIFAR-100, BiLSTM/IMDB, TCN/IMDB, and a fully connected network on Fashion-MNIST show $14-91\%$ better selective forgetting, up to $50\%$ better utility retention in relative terms (with consistent percentage-point gains on the other architectures, where a relative baseline is undefined), and unlearning-time changes ranging from $-6.7\%$ to $+6.4\%$ depending on architecture, relative to SISA.
| Comments: | This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06519 [cs.LG] |
| (or arXiv:2611.06519v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06519 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Deeraj S K [view email]
[v1]
Wed, 4 Nov 2026 13:45:32 UTC (956 KB)
来源：arXiv cs.AI · arxiv.org