Mar 19, 2021 · In this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.

Jun 3, 2021 · In this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.

Mar 19, 2021 · The main contributions of our work are as follows: • We propose to introduce adversarial learning under the AVB framework for sequential ...

Mar 19, 2021 · This work introduces the adversarial training for sequence generation under the Adversarial Variational Bayes (AVB) framework.

Compared with GAN-based methods, VAE-based methods have more stable optimization, which thus have garnered more attention in the sequential recommendation.

A two-branched VAE model with contrastive regularization as an embodiment of ContrastELBO for sequential recommendation.

Duration: 14:26
Posted: Apr 5, 2021

Oct 17, 2022 · Despite their abilities to model the uncertainty of sequential behaviors, empirical studies show that they perform worse than deterministic.

ACVAE-PyTorch ... PyTorch Code for Adversarial and Contrastive AutoEncoder for Sequential Recommendation. Usage. python 3.6+; PyTorch; tqdm; tensorboardX; numpy.

Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation. Published on Apr 13, 202116 Views ...