DECAF: De-Clustering for Adaptive Representational Unlearning

• URL: http://arxiv.org/abs/2607.23934v1
• Date: Mon, 27 Jul 2026 02:11:58 GMT
• Title: DECAF: De-Clustering for Adaptive Representational Unlearning
• Abstract summary: 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.<n>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.
• Score: 13.298390892944221
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Correlation-Guided Fast Machine Unlearning via Hessian Analysis [15.622259863184295]
  Existing unlearning techniques require repeated expensive Hessian-inverse-vector computations for each data point removal.<n>We introduce a computationally efficient unlearning framework that identifies correlated data points in the training set and applies a theoretically derived closed-form parameter update rule.<n>Our method establishes theoretical guarantees and ensures numerical stability through Hessian damping.
  arXiv  Detail & Related papers  (2026-09-11T09:21:30Z)
• Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition [53.005382593686356]
  Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision.<n>We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition.
  arXiv  Detail & Related papers  (2026-05-06T10:03:06Z)
• FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning [2.750124853532831]
  We propose FB-NLL, a feature-centric framework that decouples user clustering from iterative training dynamics.<n>Our framework consistently outperforms state-of-the-art baselines in terms of average accuracy and performance stability.
  arXiv  Detail & Related papers  (2026-04-21T17:51:58Z)
• Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization [72.20212909644017]
  Deliberate Practice Policy Optimization (DPPO) is a metacognitive Metaloop'' training framework.<n>DPPO alternates between supervised fine-tuning (competence expansion) and reinforcement learning (skill refinement)<n> Empirically, training a vision-language embodied model with DPPO, referred to as Pelican-VL 1.0, yields a 20.3% performance improvement over the base model.<n>We are open-sourcing both the models and code, providing the first systematic framework that alleviates the data and resource bottleneck.
  arXiv  Detail & Related papers  (2025-11-20T17:58:04Z)
• A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning [43.847168319564844]
  We propose an FL backdoor defense framework, named CLIP-Fed, that utilizes the zero-shot learning capabilities of vision-language pre-training models.<n>Our scheme overcomes the limitations of Non-IID imposed on defense effectiveness by integrating pre-aggregation and post-aggregation defense strategies.
  arXiv  Detail & Related papers  (2025-08-14T03:39:54Z)
• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining [53.893792844055106]
  Large language model pretraining is compute-intensive, yet many tokens contribute marginally to learning, resulting in inefficiency.<n>We introduce Selective Efficient Language Modeling, a risk-aware algorithm that improves training efficiency and distributional robustness by performing online token-level batch selection.<n> Experiments on GPT-2 pretraining show that ESLM significantly reduces training FLOPs while maintaining or improving both perplexity and downstream performance compared to baselines.
  arXiv  Detail & Related papers  (2025-05-26T12:23:26Z)
• RCC-PFL: Robust Client Clustering under Noisy Labels in Personalized Federated Learning [8.37314799155978]
  We propose a label-agnostic data similarity-based clustering algorithm, coined RCC-PFL.<n>We show that it outperforms multiple baselines in terms of average accuracy and variance reduction.
  arXiv  Detail & Related papers  (2025-03-25T17:50:54Z)
• Interaction-Aware Gaussian Weighting for Clustered Federated Learning [58.92159838586751]
  Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy.<n>We propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution.<n>Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy.
  arXiv  Detail & Related papers  (2025-02-05T16:33:36Z)
• FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Data [21.341280782748278]
  Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity inFL. We propose an adaptive CFL framework, named FedAC, which efficiently integrates global knowledge into intra-cluster learning. Experiments show that FedAC achieves superior empirical performance, increasing the test accuracy by around 1.82% and 12.67%.
  arXiv  Detail & Related papers  (2024-03-25T06:43:28Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)

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.