[论文解读] Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation

Zhe Xie, Chengxuan Liu+4 more|arXiv (Cornell University)|Mar 19, 2021

Recommender Systems and Techniques参考文献 31被引用 4

一句话总结

本文提出ACVAE，一种新颖的序列推荐模型，通过在对抗变分贝叶斯（AVB）框架下引入对抗训练和对比学习，增强了变分自编码器。通过减少潜在变量的维度间相关性并提升个性化表征学习能力，ACVAE在四个真实世界数据集上实现了最先进性能，在召回率和NDCG指标上均优于现有SOTA方法。

ABSTRACT

Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential recommendation. Recently, the generative models based on Variational Autoencoder (VAE) have shown the unique advantage in collaborative filtering. In particular, the sequential VAE model as a recurrent version of VAE can effectively capture temporal dependencies among items in user sequence and perform sequential recommendation. However, VAE-based models suffer from a common limitation that the representational ability of the obtained approximate posterior distribution is limited, resulting in lower quality of generated samples. This is especially true for generating sequences. To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation. Specifically, we first introduce the adversarial training for sequence generation under the Adversarial Variational Bayes (AVB) framework, which enables our model to generate high-quality latent variables. Then, we employ the contrastive loss. The latent variables will be able to learn more personalized and salient characteristics by minimizing the contrastive loss. Besides, when encoding the sequence, we apply a recurrent and convolutional structure to capture global and local relationships in the sequence. Finally, we conduct extensive experiments on four real-world datasets. The experimental results show that our proposed ACVAE model outperforms other state-of-the-art methods.

研究动机与目标

• 解决基于VAE的序列推荐模型中近似后验分布表征能力有限的问题。
• 通过提升生成潜在变量的质量与多样性，改善序列生成与推荐性能。
• 通过最小化潜在维度间的相关性并最大化用户间可区分性，增强个性化用户表征。
• 利用混合RNN-CNN编码器架构捕捉长期与短期序列模式。
• 验证对抗学习与对比学习组件在提升推荐性能方面的有效性。

提出的方法

• 在对抗变分贝叶斯（AVB）框架内引入对抗训练，以正则化潜在变量并减少维度间相关性。
• 采用对比损失，促使不同用户的潜在表征更加分离，从而增强个性化与泛化能力。
• 使用循环编码器（LSTM）建模用户交互序列中的长期时间依赖性。
• 在RNN之后应用一维卷积层，以捕捉序列中的局部短期模式。
• 联合优化VAE重构损失、KL散度、对抗损失与对比损失。
• 利用判别器网络区分真实与生成的潜在变量，从而提升后验近似的质量。

实验结果

研究问题

• RQ1 通过AVB进行对抗训练是否能提升序列VAE中潜在变量的质量与多样性？
• RQ2 对比学习是否能增强模型在序列推荐中区分个性化用户表征的能力？
• RQ3 与标准VAE相比，对抗学习与对比学习的结合对推荐性能有何影响？
• RQ4 CNN层在RNN编码器后对捕捉局部序列模式有何影响？
• RQ5 超参数α（对抗损失权重）与β（对比损失权重）对模型性能有何影响？

主要发现

• ACVAE在四个真实世界数据集上的Recall@10与NDCG@10指标上均优于最先进模型。
• 消融实验表明，移除AVB后性能显著下降，证实其在提升潜在变量质量方面的重要作用。
• 应用AVB后，潜在维度间的相关系数显著降低，表明维度间依赖性减少。
• 对比学习提升了模型泛化能力，当KL散度较弱时，β = 0.5时达到最优性能。
• 在RNN之后引入CNN层能更有效地捕捉局部序列模式，从而提升性能。
• 超参数分析表明，α = 0.05与β = 0.5在正则化与表征学习之间实现了最佳平衡。