ELECRec: Training sequential recommenders as discriminators
Proceedings of the 45th International ACM SIGIR Conference on Research and …, 2022•dl.acm.org
Sequential recommendation is often considered as a generative task, ie, training a
sequential encoder to generate the next item of a user's interests based on her historical
interacted items. Despite their prevalence, these methods usually require training with more
meaningful samples to be effective, which otherwise will lead to a poorly trained model. In
this work, we propose to train the sequential recommenders as discriminators rather than
generators. Instead of predicting the next item, our method trains a discriminator to …
sequential encoder to generate the next item of a user's interests based on her historical
interacted items. Despite their prevalence, these methods usually require training with more
meaningful samples to be effective, which otherwise will lead to a poorly trained model. In
this work, we propose to train the sequential recommenders as discriminators rather than
generators. Instead of predicting the next item, our method trains a discriminator to …
Sequential recommendation is often considered as a generative task, i.e., training a sequential encoder to generate the next item of a user's interests based on her historical interacted items. Despite their prevalence, these methods usually require training with more meaningful samples to be effective, which otherwise will lead to a poorly trained model. In this work, we propose to train the sequential recommenders as discriminators rather than generators. Instead of predicting the next item, our method trains a discriminator to distinguish if a sampled item is a 'real' target item or not. A generator, as an auxiliary model, is trained jointly with the discriminator to sample plausible alternative next items and will be thrown out after training. The trained discriminator is considered as the final SR model and denoted as \modelname. Experiments conducted on four datasets demonstrate the effectiveness and efficiency of the proposed approach.
![](/scholar/images/qa_favicons/acm.org.png)
以上显示的是最相近的搜索结果。 查看全部搜索结果