提出自适应图滤波框架，让推荐系统更精准稳定
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
- 设计双层优化目标，实现可学习的自适应图滤波
- 解决低频爆炸问题，提升推荐性能与训练稳定性
- 适用于传统和大模型推荐，通用性强
谱协同过滤的核心是图滤波设计，但现有方法多依赖人工调参而非可学习滤波器。我们发现这一挑战源于传统推荐目标的偏差，引发称为低频爆炸的谱现象，从根本上阻碍了图滤波的有效学习。为此，我们提出新型自适应谱图协同过滤框架ASPIRE，基于双层优化目标。在理论分析指导下，解耦滤波学习目标，实际中展现出优异的推荐性能、谱自适应性与训练稳定性。大量实验表明，所学滤波器性能媲美精心设计的任务专用方案。此外，ASPIRE在大模型驱动的协同过滤中同样有效。研究证明图滤波学习可行且具泛化能力，为协同过滤中的更表达性图神经网络开辟新路径。
原文摘要 · Abstract (English)
Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show that this challenge stems from a bias in traditional recommendation objectives, which induces a spectral phenomenon termed low-frequency explosion, thereby fundamentally hindering the effective learning of graph filters. To overcome this limitation, we propose a novel adaptive spectral graph collaborative filtering framework (ASPIRE) based on a bi-level optimization objective. Guided by our theoretical analysis, we disentangle the filter learning objective, which in turn leads to excellent recommendation performance, spectral adaptivity, and training stability in practice. Extensive experiments show our learned filters match the performance of carefully engineered task-specific designs. Furthermore, ASPIRE is equally effective in LLM-powered collaborative filtering. Our findings demonstrate that graph filter learning is viable and generalizable, paving the way for more expressive graph neural networks in collaborative filtering.
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。