[论文解读] Sequential Recommendation with Diffusion Models

Hanwen Du, Huanhuan Yuan+3 more|arXiv (Cornell University)|Apr 10, 2023

Recommender Systems and Techniques被引用 10

一句话总结

本文提出 DiffRec，一种基于扩散模型的序列推荐系统，能够将扩散过程适配到离散物品序列，实现高效的训练与推理，达到最先进的结果。

ABSTRACT

Generative models, such as Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN), have been successfully applied in sequential recommendation. These methods require sampling from probability distributions and adopt auxiliary loss functions to optimize the model, which can capture the uncertainty of user behaviors and alleviate exposure bias. However, existing generative models still suffer from the posterior collapse problem or the model collapse problem, thus limiting their applications in sequential recommendation. To tackle the challenges mentioned above, we leverage a new paradigm of the generative models, i.e., diffusion models, and present sequential recommendation with diffusion models (DiffRec), which can avoid the issues of VAE- and GAN-based models and show better performance. While diffusion models are originally proposed to process continuous image data, we design an additional transition in the forward process together with a transition in the reverse process to enable the processing of the discrete recommendation data. We also design a different noising strategy that only noises the target item instead of the whole sequence, which is more suitable for sequential recommendation. Based on the modified diffusion process, we derive the objective function of our framework using a simplification technique and design a denoise sequential recommender to fulfill the objective function. As the lengthened diffusion steps substantially increase the time complexity, we propose an efficient training strategy and an efficient inference strategy to reduce training and inference cost and improve recommendation diversity. Extensive experiment results on three public benchmark datasets verify the effectiveness of our approach and show that DiffRec outperforms the state-of-the-art sequential recommendation models.

研究动机与目标

• 在序列推荐中激励建模不确定性和曝光偏差。
• 将扩散模型引入序列推荐，并将其适配离散数据。
• 设计适合序列的前向/后向转移和有针对性的噪声策略。
• 推导可处理的目标函数并构建去噪序列推荐器。
• 提出高效的训练与推理策略，以降低成本并提高多样性。

提出的方法

• 定义一个额外的前向转移，将离散物品映射到连续隐藏表示。
• 在扩散步骤中仅对目标物品的隐藏表示加入噪声，以与下一个物品预测目标对齐。
• 引入一个反向转移，通过线性层和 softmax 将隐藏表示映射回物品分布。
• 推导一个简化的变分目标，使其简化为均方误差（MSE）损失再加上标准的推荐损失。
• 使用带有位置和扩散步嵌入的 Transformer 编码器开发去噪序列推荐器（DSR）。
• 通过步采样和重要性采样进行高效训练，以聚焦于更难的扩散步骤。

实验结果

研究问题

• RQ1 扩散模型是否能有效地适应离散序列推荐任务？
• RQ2 如何设计序列的前向和反向扩散转移，以避免后验/模型崩溃？
• RQ3 哪种目标函数表达有助于使基于扩散的序列推荐器的训练可处理？
• RQ4 高效的训练与推理策略是否能在不过高成本的前提下达到有竞争力的性能？
• RQ5 DiffRec 是否在基准数据集上实现了最先进的性能并提升多样性？

主要发现

• DiffRec 在三个公开基准上优于最先进的序列推荐系统。
• 改进的扩散过程（离散到连续的转变和目标项噪声）有效地处理序列数据。
• 推导出一个可处理的、基于 MSE 的目标，使其能够仅对每个序列进行单步扩散训练并附加一个推荐损失。
• 一种高效的训练策略，结合扩散步采样和重要性采样，在保持性能的同时降低成本。
• DSR 通过带有位置和扩散嵌入的 Transformer 实现对目标项隐藏表示的准确去噪。
• 提出推理策略以降低计算成本并提升推荐多样性。