scholar.google.com › citations
Aug 4, 2023 · ABSTRACT. Sequential recommendation aims at mining time-aware user interests through modeling sequential behaviors. Transformer, as an effective ...
We propose the Adaptive Disentangled Transformer (ADT) framework capable of simultaneously disentangling atten- tion heads in a given Transformer, as well as ...
This repository reimplements the backbone model from SASRec、Bert4Rec and STOSA. Requirements. The following libraries and versions are used in the experiments, ...
Duration: 1:51
Posted: Jul 13, 2023
Posted: Jul 13, 2023
Sequential recommendation (SR) aims to model users' dynamic preferences from their historical interactions. Recently, Transformer and convolution neural network ...
People also ask
What is sequential recommendation?
May 18, 2022 · Abstract:Sequential recommendation (SR) aims to model users dynamic preferences from a series of interactions. A pivotal challenge in user ...
[KDD23] Adaptive Disentangled Transformer for Sequential Recommendation · [CIKM22] Disentangling Past-Future Modeling in Sequential Recommendation via Dual ...
Based on historical behaviors, sequential recommendation endeavors to predict what a user prefers next. The recent efforts are mainly devoted to modeling ...
This paper proposes a disentangled contrastive learning method for recommendation that explores latent factors underlying implicit intents for interactions. We ...
Jul 15, 2022 · BERT4Rec is an effective model for sequential recommendation based on the Transformer architecture. In the original publication, ...