cs.LGNov 5, 2026

DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning

Authors: Nicolás Segura-Kunsagi, Juan Luis Suárez-Díaz, Iván Sevillano-García, Francisco Herrera

Organizations: Department of Computer Science and Artificial Intelligence (DECSAI), Andalusian Institute of Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

Abstract

Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. In real deployments, however, deletion requests arrive over time, calling for incremental class unlearning (ICU): classes are removed sequentially, previously forgotten knowledge must remain forgotten, and the remaining classes must be preserved. We present DIstributional SynthetiC rEplay for Retain-free iNcremental unlearning (DISCERN), an intervention-based class unlearning method that replaces access to the retain set with synthetic embeddings sampled from per-class parametric distributions. Unlike prototype-based replay, which assumes an isotropic Gaussian around each class centroid, DISCERN fits Euclidean (Gaussian, Laplace, Student's tt) and directional (von Mises--Fisher, Fisher--Bingham) families to each class and selects among them through statistical tests and, when none of them accepts, cross-validated log-likelihood. This design is motivated by the architecture-dependent latent geometry: transformer embeddings lie approximately on a hypersphere and concentrate around class directions, unlike those of convolutional networks. We evaluate DISCERN against seven retain-free baselines on MNIST, CIFAR-10, and CIFAR-100 with two convolutional and two transformer backbones, under single-class, multi-class, and incremental unlearning. DISCERN is competitive when classes are removed at once and is the most stable method in ICU on transformers: on ViT-B/16, after 20 sequential deletions it retains a harmonic mean of 0.7970.797, whereas the strongest method in the simultaneous setting drops from 0.9180.918 to 0.0480.048. A paired ablation shows that per-class distribution selection substantially reduces the resurfacing of previously forgotten classes, acting as a stabilizer of accumulated forgetting rather than a uniform improvement.

Figures & tables

Explore similar work

Sep 30, 2026

Unmerge: Efficient Machine Unlearning via Task Arithmetic

Approximate machine unlearning seeks to remove the influence of a forget set from a trained model without full retraining. Existing gradient-based methods require data-dependent hyperparameter search, struggle when forget and retain knowledge are entangled, and offer little insight into where unlearning actually happens inside the network. We recast unlearning through the lens of task arithmetic: if finetuning produces a merged task vector τmτ_m that combines learning on forget and retain sets, unlearning is the inverse operation that subtracts a learned forget component τFτ_F to recover the retain task vector τRτ_R. The forget signal is concentrated: at every layer, forget activations lie in a subspace spanned by a handful of dominant directions, so we factorize τFτ_F in a low-rank forget basis, which is faithful up to a small tail-eigenvalue residual and limits how far the correction can perturb retain. We then optimize three intuitive goals (match the merged vector inside the forget span, suppress leakage into the retain span, and bound the correction size) that provably bound forget leakage and retain damage in activation space. The resulting algorithm, Unmerge, is fast and powerful: on class-level unlearning with ResNet-50 on CIFAR-100 and Tiny ImageNet, it improves Tug-of-War by up to ~24% over a baseline of comparable runtime and by up to ~18% over stronger baselines that run ~5x slower, keeps membership-inference exposure at the level of retraining, and shrinks the feature-distribution gap to the retrained model, where relabeling methods leave forget features cleanly separable. Further studies show that Unmerge also applies to ViT-S/16 and scales to Llama-3.2-3B. The per-layer basis geometry that drives the algorithm also serves as a layerwise diagnostic for when and where unlearning becomes structurally hard.
Mar 11, 2026

Reference-Guided Machine Unlearning

Machine unlearning aims to remove the influence of specific training data from a model while preserving its general utility. In vision, many approximate unlearning methods pursue this goal through degradation-based heuristics, such as loss maximization or random labeling. Yet making a model worse on forget samples is not the same as making it behave as if those examples had never been seen: these signals can be poorly conditioned, destabilize optimization, and harm generalization. We argue that approximate unlearning should instead prioritize distributional indistinguishability, aligning the model's predictive behavior on forget data with that on truly unseen data. Motivated by this principle, we propose Reference-Guided Unlearning (ReGUn), a vision unlearning framework that uses disjoint held-out data to construct a principled, class-conditioned reference distribution for distillation. Rather than explicitly degrading predictions on forget examples, ReGUn guides them toward non-member behavior through held-out supervision. Across multiple architectures, natural image datasets, and forget fractions, ReGUn consistently improves the forgetting-utility trade-off relative to standard approximate baselines while closely matching retrain-like membership inference behavior. As one instantiation of this principle, the results suggest that simple objectives designed around indistinguishability can provide an effective alternative to complex degradation-based unlearning procedures.
Jul 27, 2026

DECAF: De-Clustering for Adaptive Representational Unlearning

Machine unlearning, which aims to remove the influence of specific training data from a trained model, is a key requirement for privacy, accountability, and adaptive deployment. We argue that many unlearning methods are vulnerable to a simple clustering attack, which can recover class structure in an unsupervised manner, limiting their suitability for continual deployment where removal requests must be handled reliably on demand. To address this, we propose DECAF (DE-Clustering for Adaptive Forgetting), a post-hoc method that operates only on the forget set and is designed to break the cluster. DECAF combines input noise, confidence suppression, and entropy-based output diversification to disrupt the residual feature-space structure associated with forgotten data. On CIFAR-10 with ResNet-18, DECAF attains 0.10% forget-class accuracy, 79.4% retain accuracy, and an AUS of 0.88, surpassing all other baselines. In cluster-based analysis, it attains performance comparable to that of unlearning methods that use the full training set, while being significantly more efficient. Code: https://github.com/ale256/representation_unlearning.