Modeling High-order Interactions across Multi-interests for Micro-video Recommendation

04/01/2021
by   Dong Yao, et al.
0

Personalized recommendation system has become pervasive in various video platform. Many effective methods have been proposed, but most of them didn't capture the user's multi-level interest trait and dependencies between their viewed micro-videos well. To solve these problems, we propose a Self-over-Co Attention module to enhance user's interest representation. In particular, we first use co-attention to model correlation patterns across different levels and then use self-attention to model correlation patterns within a specific level. Experimental results on filtered public datasets verify that our presented module is useful.

READ FULL TEXT

page 1

page 2

page 3

research
05/19/2022

Improving Micro-video Recommendation via Contrastive Multiple Interests

With the rapid increase of micro-video creators and viewers, how to make...
research
08/27/2019

Personalized Hashtag Recommendation for Micro-videos

Personalized hashtag recommendation methods aim to suggest users hashtag...
research
12/06/2021

Gumble Softmax For User Behavior Modeling

Recently, sequential recommendation systems are important in solving the...
research
02/09/2021

Referring Segmentation in Images and Videos with Cross-Modal Self-Attention Network

We consider the problem of referring segmentation in images and videos w...
research
05/12/2021

Looking at CTR Prediction Again: Is Attention All You Need?

Click-through rate (CTR) prediction is a critical problem in web search,...
research
08/09/2022

Improving Micro-video Recommendation by Controlling Position Bias

As the micro-video apps become popular, the numbers of micro-videos and ...
research
05/06/2022

Implicit semantic-based personalized micro-videos recommendation

With the rapid development of mobile Internet and big data, a huge amoun...

Please sign up or login with your details

Forgot password? Click here to reset