Stake the Points: Structure-Faithful Instance Unlearning

• URL: http://arxiv.org/abs/2603.12915v1
• Date: Fri, 13 Mar 2026 11:40:21 GMT
• Title: Stake the Points: Structure-Faithful Instance Unlearning
• Abstract summary: Machine unlearning (MU) aims to remove the influence of designated data while preserving the utility of retained knowledge.<n>We propose a novel structure-faithful framework that introduces stakes, i.e., semantic anchors that serve as reference points to maintain the knowledge structure.<n>Results show average gains of 32.9%, 22.5%, and 19.3% in performance, balancing the deletion-retention trade-off and enhancing generalization.
• Score: 12.36218755528715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic relations among retained instances, which existing studies often overlook. We observe that without such preservation, models suffer from progressive structural collapse, undermining both the deletion-retention balance. In this work, we propose a novel structure-faithful framework that introduces stakes, i.e., semantic anchors that serve as reference points to maintain the knowledge structure. By leveraging these anchors, our framework captures and stabilizes the semantic organization of knowledge. Specifically, we instantiate the anchors from language-driven attribute descriptions encoded by a semantic encoder (e.g., CLIP). We enforce preservation of the knowledge structure via structure-aware alignment and regularization: the former aligns the organization of retained knowledge before and after unlearning around anchors, while the latter regulates updates to structure-critical parameters. Results from image classification, retrieval, and face recognition show average gains of 32.9%, 22.5%, and 19.3% in performance, balancing the deletion-retention trade-off and enhancing generalization.

Related papers

• Knowing Beyond the Known: Reinforced Knowledge Specification for Multi-Label Class-Incremental Learning [37.885906679929796]
  We argue that the core obstacle is the model's ambiguous boundary between known and unknown knowledge.<n>We propose KBK (Knowing Beyond the Known), a reinforced knowledge specification framework that explicitly models what is known or not to unify historical, current, and prospective learning.<n> Experiments on multiple benchmarks validate the effectiveness and robustness of KBK, which surpasses prior best methods by 2.7% in Avg. Acc on MS-COCO B0-C10 setting.
  arXiv  Detail & Related papers  (2026-08-31T06:33:20Z)
• Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework [0.0]
  We introduce a new visual feature representation that encodes shape structure across multiple scales.<n>We further improve the learning dynamics and the read-out used to predict from the learned model.<n>The study targets two-dimensional shape, with class-incremental MNIST as a controlled, interpretable benchmark.
  arXiv  Detail & Related papers  (2026-07-28T10:17:54Z)
• The Illusion of High Utility in Safety Alignment of Text-to-Image Diffusion Models [49.67749928542536]
  Safety alignment of text-to-image (T2I) diffusion models aims to suppress harmful generations while preserving utility on benign prompts.<n>Recent methods often appear to deliver high safety with high utility, but this conclusion rests largely on coarse global utility metrics.<n>We show that when utility is measured with structured evaluation, this illusion breaks: onA (Text-to-Image Faithfulness evaluation with Question Answering)<n>We propose StructureAware Geometric Regularization (SAGE), a safety alignment objective that explicitly preserves embedding spread and inter-prompt relational structure.
  arXiv  Detail & Related papers  (2026-07-01T04:00:27Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• MeGU: Machine-Guided Unlearning with Target Feature Disentanglement [73.49657372882082]
  We propose a novel framework that guides unlearning through concept-aware re-alignment.<n>MeGU enables controlled and selective forgetting, effectively mitigating both under-unlearning and over-unlearning.
  arXiv  Detail & Related papers  (2026-02-19T05:20:31Z)
• Geometric-Disentangelment Unlearning [106.99160454669902]
  gradient ascent on forget samples often harms retained knowledge.<n>We propose the Geometric-disment Unlearning (GU) that decomposes any candidate forget gradient update into tangential and normal components to retain space and executes only the normal component.<n>Our method is plug-and-play and can be attached to existing gradient-based unlearning procedures to mitigate side effects.
  arXiv  Detail & Related papers  (2025-11-21T09:58:25Z)
• Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning [11.82771798674077]
  Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge.<n>But real-world visual and linguistic concepts are inherently hierarchical.<n>We propose HASTEN that anchors hierarchical information into CIL to reduce catastrophic forgetting.
  arXiv  Detail & Related papers  (2025-11-19T17:14:47Z)
• STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models [10.320062273796331]
  Large Language Models store extensive factual knowledge acquired during large-scale pre-training.<n>Knowledge editing has emerged as a promising solution for updating outdated or incorrect facts without full retraining.<n>We propose textscSteam, a semantic-level knowledge editing framework that enhances integration of updated knowledge into the model's knowledge structure.
  arXiv  Detail & Related papers  (2025-10-12T01:25:13Z)
• Pre-Forgettable Models: Prompt Learning as a Native Mechanism for Unlearning [9.512928441517811]
  Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks.<n>Traditional unlearning approaches, including retraining, activation editing, or distillation, are often expensive, fragile, and ill-suited for real-time or continuously evolving systems.<n>We introduce a prompt-based learning framework that unifies knowledge acquisition and removal within a single training phase.
  arXiv  Detail & Related papers  (2025-09-05T13:28:04Z)
• StPR: Spatiotemporal Preservation and Routing for Exemplar-Free Video Class-Incremental Learning [79.44594332189018]
  Class-Incremental Learning (CIL) seeks to develop models that continuously learn new action categories over time without previously acquired knowledge.<n>Existing approaches either rely on forgetting, raising concerns over memory and privacy, or adapt static image-based methods that neglect temporal modeling.<n>We propose a unified and exemplar-free VCIL framework that explicitly disentangles and preserves information.
  arXiv  Detail & Related papers  (2025-05-20T06:46:51Z)
• Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation [4.480310276450028]
  We propose a training strategy for a 3D LiDAR semantic segmentation model that learns structural relationships between classes through abstraction. This is achieved by implicitly modeling these relationships using a learning rule for hierarchical multi-label classification (HMC) Our detailed analysis demonstrates that this training strategy not only improves the model's confidence calibration but also retains additional information useful for downstream tasks such as fusion, prediction, and planning.
  arXiv  Detail & Related papers  (2024-04-09T08:49:01Z)
• Joint Language Semantic and Structure Embedding for Knowledge Graph Completion [66.15933600765835]
  We propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models. Our experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method.
  arXiv  Detail & Related papers  (2022-09-19T02:41:02Z)
• A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification [65.18004601366066]
  Person re-identification (Re-ID) via gait features within 3D skeleton sequences is a newly-emerging topic with several advantages. This paper proposes a self-supervised gait encoding approach that can leverage unlabeled skeleton data to learn gait representations for person Re-ID.
  arXiv  Detail & Related papers  (2020-09-05T16:06:04Z)

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.