cs.LGNov 4, 2026

IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning

Authors: Deeraj SK, Sadhana Devarajan, Tanmoy Hazra, Anupam Shukla

Organizations: The authors are with the Sardar Vallabhbhai National Institute of Technology Surat, Surat, Gujarat, India.

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 (εcert≤0.015ε_{\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%14-91\% better selective forgetting, up to 50%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%-6.7\% to +6.4%+6.4\% depending on architecture, relative to SISA.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Reference-Guided Machine Unlearning

    Mar 11, 2026Jonas Mirlach, Sonia Laguna, Julia E. VogtMachine Unlearning

  2. Less Noise, Same Certificate: Retain Sensitivity for Unlearning

    Mar 3, 2026Carolin Heinzler, Kasra Malihi, Amartya SanyalMachine Unlearning

  3. Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

    Apr 30, 2026Ishrak Hamim Mahi, Siam Ferdous, Md Sakib Sadman Badhon +4Privacy-Preserving MLMachine Unlearning