U-CAN: Utility-Aware Contrastive Attenuation for Efficient Unlearning in Generative Recommendation

TL;DR

This work proposes Utility-aware Contrastive AttenuatioN (U-CAN), a precision unlearning framework that operates on low-rank adapters that quantifies risk by contrasting activations and focuses on neurons with asymmetric responses that are highly sensitive to the forgetting set but suppressed on the retention set.

Abstract

Generative Recommendation (GenRec) typically leverages Large Language Models (LLMs) to redefine personalization as an instruction-driven sequence generation task. However, fine-tuning on user logs inadvertently encodes sensitive attributes into model parameters, raising critical privacy concerns. Existing Machine Unlearning (MU) techniques struggle to navigate this tension due to the Polysemy Dilemma, where neurons superimpose sensitive data with general reasoning patterns, leading to catastrophic utility loss under traditional gradient or pruning methods. To address this, we propose Utility-aware Contrastive AttenuatioN (U-CAN), a precision unlearning framework that operates on low-rank adapters. U-CAN quantifies risk by contrasting activations and focuses on neurons with asymmetric responses that are highly sensitive to the forgetting set but suppressed on the retention set. To safeguard performance, we introduce a utility-aware calibration mechanism that combines weight magnitudes with retention-set activation norms, assigning higher utility scores to dimensions that contribute strongly to retention performance. Unlike binary pruning, which often fragments network structure, U-CAN develop adaptive soft attenuation with a differentiable decay function to selectively down-scale high-risk parameters on LoRA adapters, suppressing sensitive retrieval pathways and preserving the topological connectivity of reasoning circuits. Experiments on two public datasets across seven metrics demonstrate that U-CAN achieves strong privacy forgetting, utility retention, and computational efficiency.

Figures (4)

• Figure 1: Comparison of our proposed U-CAN (C) with traditional methods (A,B). The traditional methods either distort shared parameters via gradient updates or break functional pathways via hard pruning, whereas we locate risky neurons via activation difference comparison and suppress high-risk parameters with continuous soft decay, achieving more precise forgetting while preserving general reasoning ability.
• Figure 2: The overall framework of U-CAN. The pipeline orchestrates three integral modules. (1) Contrastive Activation isolates entangled features by leveraging activation gaps to pinpoint privacy-sensitive neurons. (2) Utility Significance quantifies parameter importance by fusing static weight magnitudes with dynamic input intensities, ensuring core capabilities remain intact. (3) Adaptive Soft Attenuation scales down risk parameters using a continuous decay curve, maintaining network connectivity and avoiding the abrupt damage caused by binary pruning.
• Figure 3: Execution time (left) and throughput (right) for unlearning methods on ML-100k and Pantry.
• Figure 4: Impact of Risk Threshold on Unlearning Effectivenes.