用随机路径积分提升推荐解释的准确性
Fidelity-Aware Recommendation Explanations via Stochastic Path Integration
- 通过随机采样用户画像，动态构建更真实的解释路径
- 在3个模型、3个数据集上均超越基线，稳定提升解释可信度
- 适合关注推荐系统可解释性的研究者与工程师
解释保真度衡量解释是否准确反映模型的真实推理过程，在推荐系统中仍缺乏深入研究。本文提出SPINRec（基于随机路径积分的神经推荐解释方法），一种无需依赖特定模型的通用方法，将路径积分技术适配于推荐数据的稀疏性和隐式特性。为克服以往方法依赖固定或不现实基线的缺陷，SPINRec采用随机基线采样：从经验数据分布中抽取多个合理用户画像，选择最忠实的归因路径。该设计能同时捕捉已观察和未观察交互的影响，生成更稳定、个性化的解释。我们在三个模型（MF、VAE、NCF）、三个数据集（ML1M、Yahoo! Music、Pinterest）上开展迄今最全面的保真度评估，涵盖多种反事实指标，包括基于AUC的扰动曲线与固定长度诊断。SPINRec始终优于所有基线，确立了推荐解释保真性新基准。代码与评估工具已开源：https://github.com/DeltaLabTLV/SPINRec。
原文摘要 · Abstract (English)
Explanation fidelity, which measures how accurately an explanation reflects a model's true reasoning, remains critically underexplored in recommender systems. We introduce SPINRec (Stochastic Path Integration for Neural Recommender Explanations), a model-agnostic approach that adapts path-integration techniques to the sparse and implicit nature of recommendation data. To overcome the limitations of prior methods, SPINRec employs stochastic baseline sampling: instead of integrating from a fixed or unrealistic baseline, it samples multiple plausible user profiles from the empirical data distribution and selects the most faithful attribution path. This design captures the influence of both observed and unobserved interactions, yielding more stable and personalized explanations. We conduct the most comprehensive fidelity evaluation to date across three models (MF, VAE, NCF), three datasets (ML1M, Yahoo! Music, Pinterest), and a suite of counterfactual metrics, including AUC-based perturbation curves and fixed-length diagnostics. SPINRec consistently outperforms all baselines, establishing a new benchmark for faithful explainability in recommendation. Code and evaluation tools are publicly available at https://github.com/DeltaLabTLV/SPINRec.
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。