提出GUDA方法，快速定位扩散模型生成结果的主因训练组别
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
- 用机器遗忘替代重训，通过对比全量模型与去组模型的似然差异
- 在CIFAR-10上比完整重训快100倍，准确识别主要贡献组别
- 适合需要理解生成结果背后数据来源的研究者和开发者
视觉生成模型的训练数据归属旨在识别影响特定输出的训练数据。现有方法多针对单个样本评分，但从业者常需组级别答案（如艺术风格或物体类别）。组级归因是反事实的：若某组数据未参与训练，模型对生成样本的行为会如何变化？自然实现方式为留一组外出（LOGO）重训，但随着组数增加计算成本急剧上升。本文提出针对扩散模型的GUDA方法，通过在共享全数据模型上应用机器遗忘，近似每个反事实模型，而非从头训练。GUDA使用基于似然的评分规则（ELBO）差值量化组影响。在CIFAR-10和Stable Diffusion艺术风格归因实验中，GUDA比语义相似性、梯度归因及实例级遗忘方法更可靠地识别主贡献组，且在CIFAR-10上相较LOGO重训提速约100倍。
原文摘要 · Abstract (English)
Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or object classes). Group-wise attribution is counterfactual: how would a model's behavior on a generated sample change if a group were absent from training? A natural realization of this counterfactual is Leave-One-Group-Out (LOGO) retraining, which retrains the model with each group removed; however, it becomes computationally prohibitive as the number of groups grows. We propose GUDA (Group Unlearning-based Data Attribution) for diffusion models, which approximates each counterfactual model by applying machine unlearning to a shared full-data model instead of training from scratch. GUDA quantifies group influence using differences in a likelihood-based scoring rule (ELBO) between the full model and each unlearned counterfactual. Experiments on CIFAR-10 and artistic style attribution with Stable Diffusion show that GUDA identifies primary contributing groups more reliably than semantic similarity, gradient-based attribution, and instance-level unlearning approaches, while achieving ~100x speedup on CIFAR-10 over LOGO retraining.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。