The need to selectively and efficiently erase learned information from deep neural networks is becoming increasingly important for privacy, regulatory compliance, and adaptive system design. We introduce Graph-Propagated Projection Unlearning (GPPU), a unified and scalable algorithm for class-level unlearning that operates across both vision and audio models. GPPU employs graph-based propagation to identify class-specific directions in the feature space and projects representations onto the orthogonal subspace, followed by targeted fine-tuning, to ensure that target class information is effectively and irreversibly removed. Through comprehensive evaluations on six vision datasets and two large-scale audio benchmarks spanning a variety of architectures including CNNs, Vision Transformers, and Audio Transformers, we demonstrate that GPPU achieves highly efficient unlearning, realizing 10-20x speedups over prior methodologies while preserving model utility on retained classes. Our framework provides a principled and modality-agnostic approach to machine unlearning, evaluated at a scale that has received limited attention in prior work, contributing toward more efficient and responsible deep learning.

翻译：从深度神经网络中选择性且高效地擦除已学信息的需求，对于隐私保护、法规合规以及自适应系统设计日益重要。我们提出图传播投影遗忘（Graph-Propagated Projection Unlearning, GPPU）算法——一种适用于视觉与音频模型的统一、可扩展的类别级遗忘方法。GPPU通过基于图的传播机制识别特征空间中与目标类别相关的方向，将特征表示投影到正交子空间，并结合定向微调，确保目标类别信息被有效且不可逆地移除。在涵盖CNN、视觉Transformer及音频Transformer等多种架构的六个视觉数据集与两个大规模音频基准上的综合评估表明，GPPU实现了高效的遗忘效果，在保留模型对非目标类别实用性的同时，相较于现有方法取得了10-20倍的加速。本框架提供了一种原则性且跨模态的机器遗忘方法，其评估规模在以往研究中较少受到关注，为构建更高效且负责任的深度学习系统做出贡献。