通过对称对比学习提升评论增强推荐的鲁棒性
SymCERE: Symmetric Contrastive Learning for Robust Review-Enhanced Recommendation
- 设计对称NCE损失，利用完整交互历史消除假负样本
- 引入L2归一化缓解流行度偏差，提升模型稳定性
- 在原始评论上验证效果，适合追求可解释性的推荐系统
现代推荐系统融合用户行为图与评论文本，但常因假负样本、流行度偏差和信号模糊导致融合鸿沟。本文提出SymCERE（对称NCE），一种通过结构几何对齐弥合该鸿沟的对比学习框架。首先，设计对称NCE损失，利用完整交互历史排除假负样本；其次，引入L2归一化以结构性中和流行度偏差。在15个数据集（电商、本地点评、旅游）上的实验表明，SymCERE优于强基线，NDCG@10最高提升43.6%。尤其在原始评论（含显著噪声）上验证有效。分析揭示‘语义锚定’现象：模型聚焦客观词汇（如'OEM'、'gasket'）而非通用情感，说明有效对齐源于提取事实属性，为构建鲁棒、可解释系统提供路径。代码已公开于https://anonymous.4open.science/r/ReviewGNN-2E1E。
原文摘要 · Abstract (English)
Modern recommendation systems fuse user behavior graphs and review texts but often encounter a "Fusion Gap" caused by False Negatives, Popularity Bias, and Signal Ambiguity. We propose SymCERE (Symmetric NCE), a contrastive learning framework bridging this gap via structural geometric alignment. First, we introduce a symmetric NCE loss that leverages full interaction history to exclude false negatives. Second, we integrate L2 normalization to structurally neutralize popularity bias. Experiments on 15 datasets (e-commerce, local reviews, travel) demonstrate that SymCERE outperforms strong baselines, improving NDCG@10 by up to 43.6%. Notably, we validate this on raw reviews, addressing significant noise. Analysis reveals "Semantic Anchoring," where the model aligns on objective vocabulary (e.g., "OEM," "gasket") rather than generic sentiment. This indicates effective alignment stems from extracting factual attributes, offering a path toward robust, interpretable systems. The code is available at https://anonymous.4open.science/r/ReviewGNN-2E1E.
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。