Erase at the Core: Representation Unlearning for Machine Unlearning

• URL: http://arxiv.org/abs/2602.05375v1
• Date: Thu, 05 Feb 2026 06:54:44 GMT
• Title: Erase at the Core: Representation Unlearning for Machine Unlearning
• Authors: Jaewon Lee, Yongwoo Kim, Donghyun Kim,
• Abstract summary: Erase at the Core (EC) is a framework designed to enforce forgetting throughout the entire network hierarchy.<n>EC integrates contrastive unlearning on the forget set with retain set preservation through deeply supervised learning.<n>EC is model-agnostic and can be incorporated as a plug-in module into existing unlearning methods.
• Score: 11.77697706755224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many approximate machine unlearning methods demonstrate strong logit-level forgetting -- such as near-zero accuracy on the forget set -- yet continue to preserve substantial information within their internal feature representations. We refer to this discrepancy as superficial forgetting. Recent studies indicate that most existing unlearning approaches primarily alter the final classifier, leaving intermediate representations largely unchanged and highly similar to those of the original model. To address this limitation, we introduce the Erase at the Core (EC), a framework designed to enforce forgetting throughout the entire network hierarchy. EC integrates multi-layer contrastive unlearning on the forget set with retain set preservation through deeply supervised learning. Concretely, EC attaches auxiliary modules to intermediate layers and applies both contrastive unlearning and cross-entropy losses at each supervision point, with layer-wise weighted losses. Experimental results show that EC not only achieves effective logit-level forgetting, but also substantially reduces representational similarity to the original model across intermediate layers. Furthermore, EC is model-agnostic and can be incorporated as a plug-in module into existing unlearning methods, improving representation-level forgetting while maintaining performance on the retain set.

Related papers

• Grokked Models are Better Unlearners [5.8757712547216485]
  Starting from grokked checkpoints consistently yields more efficient forgetting.<n>Post-grokking models learn more modular representations with reduced gradient alignment between forget and retain subsets.
  arXiv  Detail & Related papers  (2025-12-03T04:35:49Z)
• POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse [12.913395960667161]
  In computer vision, machine unlearning aims to remove the influence of specific visual concepts or training images without retraining from scratch.<n>We extend the notion of unlearning to the representation level, deriving a three-term interplay between forgetting efficacy, retention fidelity, and class separation.<n>Experiments on CIFAR-10/100 and PathMNIST demonstrate that POUR achieves effective unlearning while preserving retained knowledge, outperforming state-of-the-art unlearning methods on both classification-level and representation-level metrics.
  arXiv  Detail & Related papers  (2025-11-24T17:38:53Z)
• Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy [65.15943255667733]
  We introduce Subnetwork Image Translation ADDA with automatic depth selection (SIT-ADDA-Auto)<n>We show that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer.<n>Our results provide a design rule for label-free adaptation in microscopy and a recipe for field settings; the code is publicly available.
  arXiv  Detail & Related papers  (2025-11-15T03:01:05Z)
• Exploring Structural Degradation in Dense Representations for Self-supervised Learning [84.52554180480037]
  We observe a counterintuitive phenomenon in self-supervised learning (SSL): longer training may impair the performance of dense prediction tasks.<n>We refer to this phenomenon as Self-supervised Dense Degradation (SDD) and demonstrate its consistent presence across sixteen state-of-the-art SSL methods.<n>We introduce a Dense representation Structure Estimator (DSE) composed of a class-relevance measure and an effective dimensionality measure.
  arXiv  Detail & Related papers  (2025-10-20T08:40:16Z)
• Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech [51.14752758616364]
  Speech-based depression detection (SDD) is a promising, non-invasive alternative to traditional clinical assessments.<n>We propose HAREN-CTC, a novel architecture that integrates multi-layer SSL features using cross-attention within a multitask learning framework.<n>The model achieves state-of-the-art macro F1-scores of 0.81 on DAIC-WOZ and 0.82 on MODMA, outperforming prior methods across both evaluation scenarios.
  arXiv  Detail & Related papers  (2025-10-05T09:32:12Z)
• Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models [15.847302755988506]
  We address the Continual Learning problem, wherein a model must learn a sequence of tasks from non-stationary distributions. We propose LayUP, a new prototype-based approach to CL that leverages second-order feature statistics from multiple intermediate layers of a pre-trained network. Our results demonstrate that fully exhausting the representational capacities of pre-trained models in CL goes well beyond their final embeddings.
  arXiv  Detail & Related papers  (2023-12-13T13:11:44Z)
• AttenScribble: Attentive Similarity Learning for Scribble-Supervised Medical Image Segmentation [5.8447004333496855]
  In this paper, we present a straightforward yet effective scribble supervised learning framework. We create a pluggable spatial self-attention module which could be attached on top of any internal feature layers of arbitrary fully convolutional network (FCN) backbone. This attentive similarity leads to a novel regularization loss that imposes consistency between segmentation prediction and visual affinity.
  arXiv  Detail & Related papers  (2023-12-11T18:42:18Z)
• Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation [15.353256018248103]
  LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding. We present a coarse-to-fine setup that LEArns from classification mistaKes (LEAK) derived from a standard model. Our LEAK approach is very general and can be seamlessly applied on top of any segmentation architecture.
  arXiv  Detail & Related papers  (2023-01-26T14:52:30Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• Self-Distilled Self-Supervised Representation Learning [35.60243157730165]
  State-of-the-art frameworks in self-supervised learning have recently shown that fully utilizing transformer-based models can lead to performance boost. In our work, we further exploit this by allowing the intermediate representations to learn from the final layers via the contrastive loss. Our method, Self-Distilled Self-Supervised Learning (SDSSL), outperforms competitive baselines (SimCLR, BYOL and MoCo v3) using ViT on various tasks and datasets.
  arXiv  Detail & Related papers  (2021-11-25T07:52:36Z)
• Flip Learning: Erase to Segment [65.84901344260277]
  Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. We propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning.
  arXiv  Detail & Related papers  (2021-08-02T09:56:10Z)
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation [64.91560451900125]
  State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results. Few-shot segmentation is proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information.
  arXiv  Detail & Related papers  (2020-08-04T10:41:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.