[论文解读] A Simple but Hard-to-Beat Baseline for Session-based Recommendations.

Fajie Yuan, Alexandros Karatzoglou+3 more|arXiv (Cornell University)|Aug 15, 2018

Generative Adversarial Networks and Image Synthesis参考文献 20被引用 9

一句话总结

该论文提出了一种基于CNN的简单但非常有效的会话推荐模型，通过空洞卷积和残差块捕捉用户行为序列中的短程与长程依赖关系。该模型在减少训练时间的同时实现了最先进（SOTA）的准确率，为未来的研究建立了强有力的基线。

ABSTRACT

Convolutional Neural Networks (CNNs) models have been recently introduced in the domain of top-$N$ session-based recommendations. An ordered collection of past items the user has interacted with in a session (or sequence) are embedded into a 2-dimensional latent matrix, and treated as an image. The convolution and pooling operations are then applied to the mapped item embeddings. In this paper, we first examine the typical session-based CNN recommender and show that both the generative model and network architecture are suboptimal when modeling long-range dependencies in the item sequence. To address the issues, we propose a simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range dependencies. The network architecture of the proposed model is formed of a stack of holed convolutional layers, which can efficiently increase the receptive fields without relying on the pooling operation. Another contribution is the effective use of residual block structure in recommender systems, which can ease the optimization for much deeper networks. The proposed generative model attains state-of-the-art accuracy with less training time in the session-based recommendation task. It accordingly can be used as a powerful session-based recommendation baseline to beat in future, especially when there are long sequences of user feedback.

研究动机与目标

• 解决现有基于CNN的会话推荐模型在建模用户交互序列长程依赖关系方面的局限性。
• 改进生成模型与网络架构，以在序列用户行为中实现更好的表征学习。
• 在保持或提升推荐准确率的同时，减少训练时间。
• 开发一种鲁棒且易于实现的基线模型，尤其在长会话序列上优于现有方法。

提出的方法

• 该模型使用项目序列的2D潜在矩阵表示，将序列视为图像进行卷积处理。
• 采用空洞（空隙）卷积层扩展感受野，而无需下采样，从而实现对长程依赖关系的更好建模。
• 在网络架构中集成残差块，以促进深层网络的训练并改善优化。
• 生成模型通过过去交互序列预测会话中的下一个项目进行训练。
• 该架构避免使用最大池化操作，转而依赖空洞卷积以保持空间分辨率并捕捉序列模式。
• 项目嵌入通过可学习的嵌入层学习得到，作为2D卷积堆叠的输入。

实验结果

研究问题

• RQ1 更简单的CNN架构结合空洞卷积是否能在会话推荐任务中超越现有模型？
• RQ2 与标准卷积和池化层相比，空洞卷积在用户会话序列中建模长程依赖关系的效率如何？
• RQ3 残差块在深层会话推荐网络中在多大程度上提升了训练稳定性和性能？
• RQ4 与先前方法相比，所提出的模型是否在减少训练时间的同时实现了最先进准确率？

主要发现

• 所提出的模型在标准会话推荐基准上实现了最先进准确率。
• 与以往基于CNN的模型相比，该模型显著减少了训练时间，同时保持或提升了性能。
• 使用空洞卷积使模型能够在不依赖池化操作的情况下有效建模长程依赖关系。
• 残差块的集成使得更深的网络架构成为可能，同时优化和性能均得到改善。
• 该模型建立了一个强大且简洁的基线，极难被超越，尤其在长用户会话序列上表现突出。