用于多域 CTR 预测的 MoE-MLoRA：通过专家专精实现高效适配
MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
AI总结：
提出 MoE-MLoRA 混合专家框架，通过独立域专家训练与动态门控加权提升多域 CTR 预测，在八个模型和两个数据集上验证其优势及调参必要性。
摘要：
个性化推荐系统必须适配用户在不同域中的交互。传统方法（如 MLoRA）对每个域应用单一适配，但在处理多样化用户行为时缺乏灵活性。为解决这一问题，我们提出 MoE-MLoRA，这是一个混合专家框架：每个专家首先接受独立训练以专精于其所在域，随后训练门控网络来动态加权各专家的贡献。我们在 Movielens 和 Taobao 上跨八个 CTR 模型评估 MoE-MLoRA，结果表明它在大规模动态数据集上提升了性能（在 Taobao-20 上 Weighted-AUC 提高 1.45），但在域多样性和稀疏性较低的结构化数据集上收益有限。对每个域专家数量的进一步分析表明，更大的集成并不总能提升性能，这说明需要进行模型感知的调优。我们的发现凸显了基于专家的架构在多域推荐系统中的潜力，证明任务感知专精和自适应门控能够在复杂环境中提高预测准确率。实现和代码可在我们的 GitHub 仓库获取。
英文摘要：
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Movielens and Taobao, showing that it improves performance in large-scale, dynamic datasets (+1.45 Weighed-AUC in Taobao-20) but offers limited benefits in structured datasets with low domain diversity and sparsity. Further analysis of the number of experts per domain reveals that larger ensembles do not always improve performance, indicating the need for model-aware tuning. Our findings highlight the potential of expert-based architectures for multi-domain recommendation systems, demonstrating that task-aware specialization and adaptive gating can enhance predictive accuracy in complex environments. The implementation and code are available in our GitHub repository.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
