Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation

06/11/2021
by   Ziwei Fan, et al.
0

The sequential patterns within the user interactions are pivotal for representing the user's preference and capturing latent relationships among items. The recent advancements of sequence modeling by Transformers advocate the community to devise more effective encoders for the sequential recommendation. Most existing sequential methods assume users are deterministic. However, item-item transitions might fluctuate significantly in several item aspects and exhibit randomness of user interests. This stochastic characteristics brings up a solid demand to include uncertainties in representing sequences and items. Additionally, modeling sequences and items with uncertainties expands users' and items' interaction spaces, thus further alleviating cold-start problems. In this work, we propose a Distribution-based Transformer for Sequential Recommendation (DT4SR), which injects uncertainties into sequential modeling. We use Elliptical Gaussian distributions to describe items and sequences with uncertainty. We describe the uncertainty in items and sequences as Elliptical Gaussian distribution. And we adopt Wasserstein distance to measure the similarity between distributions. We devise two novel Trans-formers for modeling mean and covariance, which guarantees the positive-definite property of distributions. The proposed method significantly outperforms the state-of-the-art methods. The experiments on three benchmark datasets also demonstrate its effectiveness in alleviating cold-start issues. The code is available inhttps://github.com/DyGRec/DT4SR.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/16/2022

Sequential Recommendation via Stochastic Self-Attention

Sequential recommendation models the dynamics of a user's previous behav...
research
05/02/2021

Augmenting Sequential Recommendation with Pseudo-Prior Items via Reversely Pre-training Transformer

Sequential Recommendation characterizes the evolving patterns by modelin...
research
04/03/2023

DiffuRec: A Diffusion Model for Sequential Recommendation

Mainstream solutions to Sequential Recommendation (SR) represent items w...
research
12/16/2022

Uniform Sequence Better: Time Interval Aware Data Augmentation for Sequential Recommendation

Sequential recommendation is an important task to predict the next-item ...
research
04/14/2023

Learning Graph ODE for Continuous-Time Sequential Recommendation

Sequential recommendation aims at understanding user preference by captu...
research
01/28/2023

Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation

Self-supervised sequential recommendation significantly improves recomme...
research
08/05/2023

ConvFormer: Revisiting Transformer for Sequential User Modeling

Sequential user modeling, a critical task in personalized recommender sy...

Please sign up or login with your details

Forgot password? Click here to reset