arXiv:2608.30487v1 Announce Type: cross Abstract: Deep networks trained on noisy labels simultaneously generalize on clean data and memorize flipped labels. These are usually conflated as pressures o...
arXiv:2605.10795v2 Announce Type: replace-cross Abstract: Large language models excel at factual recall, yet the fundamental limits of storing input--output associations with neural networks remain u...
arXiv:2605.06240v2 Announce Type: replace-cross Abstract: Forward-Forward (FF) training lets each layer learn from a local goodness criterion. In cumulative-goodness variants, later layers can inheri...
arXiv:2603.25579v2 Announce Type: replace-cross Abstract: A key capability of modern neural networks is their capacity to simultaneously learn underlying rules and memorize specific facts or exceptio...
arXiv:2605. 20282v3 Announce Type: replace-cross Abstract: Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics.
arXiv:2606. 27855v1 Announce Type: cross Abstract: Deep learning models for surface electromyography (sEMG) can benefit substantially from subject-specific (re-)calibration, since no sufficiently large and diverse datasets are available to train fully generic decoders.
The paper introduces Unmerge, an efficient machine unlearning algorithm that treats unlearning as the inverse of task arithmetic. By representing the forget component as a low‑rank basis at each layer, Unmerge optimizes three goals—matching the merged vector, suppressing leakage, and bounding correction size—to limit forget leakage and retain damage. Experiments on ResNet‑50, ViT‑S/16, and Llama‑3.2‑3B show significant performance gains over existing methods while maintaining privacy and feature‑distribution fidelity.
arXiv:2602. 13298v4 Announce Type: replace-cross Abstract: This paper presents a controlled comparative study of convolutional neural network (CNN) topology and image classification performance across the architectural families VGG, ResNet, and GoogLeNet, evaluated on CIFAR-10 under a unified training protocol.
DISCERN is a class‑unlearning method that replaces real data with synthetic embeddings drawn from per‑class parametric distributions, selecting the best fit via statistical tests or cross‑validated likelihood. Unlike prototype replay, it models both Euclidean (Gaussian, Laplace, Student’s t) and directional (von Mises–Fisher, Fisher–Bingham) families to capture the latent geometry of transformer embeddings, which lie on a hypersphere. Experiments on MNIST, CIFAR‑10, and CIFAR‑100 with convolutional and transformer backbones show DISCERN performs competitively in simultaneous deletions and remains the most stable in incremental class unlearning, especially on ViT‑B/16 where it maintains a high harmonic mean after 20 sequential deletions.
arXiv:2607. 11541v1 Announce Type: new Abstract: We introduce a straightforward yet effective method to empirically study memorization in deep neural networks for classification tasks.
arXiv:2609.24379v1 Announce Type: cross Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entan...
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,...