Controllable Machine Unlearning via Gradient Pivoting

• URL: http://arxiv.org/abs/2510.19226v1
• Date: Wed, 22 Oct 2025 04:20:24 GMT
• Title: Controllable Machine Unlearning via Gradient Pivoting
• Authors: Youngsik Hwang, Dong-Young Lim,
• Abstract summary: We introduce Controllable Unlearning by Pivoting Gradient (CUP), which features a unique pivoting mechanism.<n>Unlike traditional MOO methods that converge to a single solution, CUP's mechanism is designed to controllably navigate the entire Pareto frontier.
• Score: 8.694405135908482
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Machine unlearning (MU) aims to remove the influence of specific data from a trained model. However, approximate unlearning methods, often formulated as a single-objective optimization (SOO) problem, face a critical trade-off between unlearning efficacy and model fidelity. This leads to three primary challenges: the risk of over-forgetting, a lack of fine-grained control over the unlearning process, and the absence of metrics to holistically evaluate the trade-off. To address these issues, we reframe MU as a multi-objective optimization (MOO) problem. We then introduce a novel algorithm, Controllable Unlearning by Pivoting Gradient (CUP), which features a unique pivoting mechanism. Unlike traditional MOO methods that converge to a single solution, CUP's mechanism is designed to controllably navigate the entire Pareto frontier. This navigation is governed by a single intuitive hyperparameter, the `unlearning intensity', which allows for precise selection of a desired trade-off. To evaluate this capability, we adopt the hypervolume indicator, a metric that captures both the quality and diversity of the entire set of solutions an algorithm can generate. Our experimental results demonstrate that CUP produces a superior set of Pareto-optimal solutions, consistently outperforming existing methods across various vision tasks.

Related papers

• A General and Streamlined Differentiable Optimization Framework [10.851559133306196]
  This paper presents the DiffOptl interface for Julia optimization framework.<n>A first-class JuMP-native API allows users to obtain named parameters derivatives directly with respect to them.<n>Results demonstrate that differentiing a routine can be as a training tool for experimentation, learning, and design-without deviating from standard JuMP modeling practices.
  arXiv  Detail & Related papers  (2025-10-29T21:42:36Z)
• Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery [30.346382763036598]
  Machine unlearning (MU) aims to efficiently remove sensitive or harmful memory from a pre-trained model.<n>The key challenge is to balance the potential tradeoff between unlearning efficacy and utility preservation.<n>We propose an implicit gradient surgery method, which approximates the solution to a constrained optimization problem via only one backpropagation.
  arXiv  Detail & Related papers  (2025-10-25T02:49:26Z)
• Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate [105.86576388991713]
  We introduce a normalized gradient difference (NGDiff) algorithm, enabling us to have better control over the trade-off between the objectives.<n>We provide a theoretical analysis and empirically demonstrate the superior performance of NGDiff among state-of-the-art unlearning methods on the TOFU and MUSE datasets.
  arXiv  Detail & Related papers  (2024-10-29T14:41:44Z)
• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling on a continuous domain for the data prediction task of (multimodal) self-supervised representation learning.<n>We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.<n>We propose a novel non-parametric method for approximating the sum of conditional probability densities required by MIS.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• M$^{2}$M: Learning controllable Multi of experts and multi-scale operators are the Partial Differential Equations need [43.534771810528305]
  This paper introduces a framework of multi-scale and multi-expert (M$2$M) neural operators to simulate and learn PDEs efficiently. We employ a divide-and-conquer strategy to train a multi-expert gated network for the dynamic router policy. Our method incorporates a controllable prior gating mechanism that determines the selection rights of experts, enhancing the model's efficiency.
  arXiv  Detail & Related papers  (2024-10-01T15:42:09Z)
• Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization [30.54462829263857]
  We study the machine unlearning problem in Image-to-Image (I2I) generative models.<n>Previous studies mainly treat it as a single objective optimization problem, offering a solitary solution.<n>We propose a controllable unlearning framework that uses a control coefficient $varepsilon$ to control the trade-off.
  arXiv  Detail & Related papers  (2024-08-03T07:04:55Z)
• Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [53.33473557562837]
  Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost. We propose a practical and scalable approach to solve this problem via mixture of experts (MoE) based model fusion. By ensembling the weights of specialized single-task models, the MoE module can effectively capture the trade-offs between multiple objectives.
  arXiv  Detail & Related papers  (2024-06-14T07:16:18Z)
• UCB-driven Utility Function Search for Multi-objective Reinforcement Learning [51.00436121587591]
  In Multi-objective Reinforcement Learning (MORL) agents are tasked with optimising decision-making behaviours.<n>We focus on the case of linear utility functions parametrised by weight vectors w.<n>We introduce a method based on Upper Confidence Bound to efficiently search for the most promising weight vectors during different stages of the learning process.
  arXiv  Detail & Related papers  (2024-05-01T09:34:42Z)
• Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach [38.76462300149459]
  We develop a Multi-objective Correction (MoCo) method for multi-objective gradient optimization. The unique feature of our method is that it can guarantee convergence without increasing the non fairness gradient.
  arXiv  Detail & Related papers  (2022-10-23T05:54:26Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• MAML is a Noisy Contrastive Learner [72.04430033118426]
  Model-agnostic meta-learning (MAML) is one of the most popular and widely-adopted meta-learning algorithms nowadays. We provide a new perspective to the working mechanism of MAML and discover that: MAML is analogous to a meta-learner using a supervised contrastive objective function. We propose a simple but effective technique, zeroing trick, to alleviate such interference.
  arXiv  Detail & Related papers  (2021-06-29T12:52:26Z)

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.