发表机构
Stevens Institute of Technology; University of Maryland, College Park（史蒂文斯理工学院; 马里兰大学学院公园分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出无需训练的符号感知谱协同过滤框架DualSpectralCF，将显式负反馈融入谱协同过滤，在5个基准数据集上超越原骨干，速度远快于SIGformer，冷启动用户收益显著。
AI 中文摘要
现实世界的推荐平台通常会收集显式负反馈，例如1星评价、“讨厌”按钮点击、用户间不信任以及观看率极低的视频。已有的符号感知推荐器会利用这类信号来显著提升准确率，但需以基于梯度的训练为代价。与此同时，一系列无需训练的谱协同过滤方法仅基于正交互，就能以极低的成本达到或超越基于学习的图推荐器的性能。本文将这两类方法结合，提出了DualSpectralCF，这是一个无需训练的框架，包含两个可附加到任意形式为$\boldsymbol{\r}_u = F(\boldsymbol{M})$的谱骨干的组件：编码用户显式厌恶的符号输入信号$\boldsymbol{\r}_u^{\boldsymbol{\rm \textpm}}$，以及将相似项与厌恶项分别聚合的符号项-项算子$\boldsymbol{M}^{\boldsymbol{\rm \textpm}}$。该框架与骨干无关，仅需添加两个标量超参数。我们在ChebyCF、GF-CF和Turbo-CF上实例化DualSpectralCF，并在5个符号感知基准上进行评估：所有实例在全部5个数据集上均达到或超越其无符号骨干的性能，采用骨干特定的$(\boldsymbol{\rm \textgamma}, \boldsymbol{\rm \textkappa})$调优时Recall@20提升最高达+32.6%，固定默认$(\boldsymbol{\rm \textgamma} = -0.5, \boldsymbol{\rm \textkappa} = 0.1)$时DualSpectralCF-Cheby的Recall@20提升为+1.9%至+16.0%，该系列方法的运行速度比SIGformer快7.7至155.3倍，同时达到其准确率的70.7%至90.7%。符号感知对冷启动用户帮助最大，在拥有1至5个训练项的Epinions用户上，Recall@20提升最高达+29.2%。
英文摘要
Real-world recommendation platforms routinely collect explicit negative feedback such as 1-star reviews, hate-button clicks, distrust between users, and very-low watch-ratio videos. Learned sign-aware recommenders exploit this signal for clear accuracy gains, but only at the cost of gradient-based training. In parallel, a line of training-free spectral collaborative filtering methods matches or beats learned graph recommenders at a fraction of the cost, yet operates on positive interactions alone. We bridge these two lines with DualSpectralCF, a training-free framework of two components that attach to any spectral backbone of the form $\hat{\mathbf{r}}_u = F(\mathbf{M}) \mathbf{r}_u$: a signed input signal $\mathbf{r}_u^{\pm}$ that encodes the user's explicit dislikes, and a signed item-item operator $\mathbf{M}^{\pm}$ that blends like-together and dislike-together similarity. The framework is backbone-agnostic and adds just two scalar hyperparameters. We instantiate DualSpectralCF on ChebyCF, GF-CF, and Turbo-CF, and evaluate on five sign-aware benchmarks: every instance matches or beats its unsigned backbone on all 5 datasets, with Recall@20 lifts up to +32.6% with backbone-specific $(γ, κ)$ tuning and +1.9% to +16.0% for DualSpectralCF-Cheby at the fixed default $(γ= -0.5, κ= 0.1)$, and the family runs 7.7 to 155.3$\times$ faster than SIGformer while reaching 70.7% to 90.7% of its accuracy. Sign-awareness helps most for cold-start users, with up to +29.2% Recall@20 on Epinions users with 1 to 5 training items.
CommentsAccepted at CIKM 2026. Code: https://github.com/guanqun-yang/DualSpectralCF
