Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GLoCIM: Global-view Long Chain Interest Modeling for news recommendation

Zhen Yang, Wenhui Wang, Tao Qi, Peng Zhang, Tianyun Zhang, Ru Zhang, Jianyi Liu, Yongfeng Huang

TL;DR

A Global-view Long Chain Interests Modeling for news recommendation (GLoCIM) is proposed, which combines neighbor interest with long chain interest distilled from a global click graph, leveraging the collaboration among similar users to enhance news recommendation.

Abstract

Accurately recommending candidate news articles to users has always been the core challenge of news recommendation system. News recommendations often require modeling of user interest to match candidate news. Recent efforts have primarily focused on extracting local subgraph information in a global click graph constructed by the clicked news sequence of all users. Howerer, the computational complexity of extracting global click graph information has hindered the ability to utilize far-reaching linkage which is hidden between two distant nodes in global click graph collaboratively among similar users. To overcome the problem above, we propose a Global-view Long Chain Interests Modeling for news recommendation (GLoCIM), which combines neighbor interest with long chain interest distilled from a global click graph, leveraging the collaboration among similar users to enhance news recommendation. We therefore design a long chain selection algorithm and long chain interest encoder to obtain global-view long chain interest from the global click graph. We design a gated network to integrate long chain interest with neighbor interest to achieve the collaborative interest among similar users. Subsequently we aggregate it with local news category-enhanced representation to generate final user representation. Then candidate news representation can be formed to match user representation to achieve news recommendation. Experimental results on real-world datasets validate the effectiveness of our method to improve the performance of news recommendation.

GLoCIM: Global-view Long Chain Interest Modeling for news recommendation

TL;DR

A Global-view Long Chain Interests Modeling for news recommendation (GLoCIM) is proposed, which combines neighbor interest with long chain interest distilled from a global click graph, leveraging the collaboration among similar users to enhance news recommendation.

Abstract

Accurately recommending candidate news articles to users has always been the core challenge of news recommendation system. News recommendations often require modeling of user interest to match candidate news. Recent efforts have primarily focused on extracting local subgraph information in a global click graph constructed by the clicked news sequence of all users. Howerer, the computational complexity of extracting global click graph information has hindered the ability to utilize far-reaching linkage which is hidden between two distant nodes in global click graph collaboratively among similar users. To overcome the problem above, we propose a Global-view Long Chain Interests Modeling for news recommendation (GLoCIM), which combines neighbor interest with long chain interest distilled from a global click graph, leveraging the collaboration among similar users to enhance news recommendation. We therefore design a long chain selection algorithm and long chain interest encoder to obtain global-view long chain interest from the global click graph. We design a gated network to integrate long chain interest with neighbor interest to achieve the collaborative interest among similar users. Subsequently we aggregate it with local news category-enhanced representation to generate final user representation. Then candidate news representation can be formed to match user representation to achieve news recommendation. Experimental results on real-world datasets validate the effectiveness of our method to improve the performance of news recommendation.
Paper Structure (23 sections, 16 equations, 5 figures, 4 tables, 1 algorithm)

This paper contains 23 sections, 16 equations, 5 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Category-enhanced news Representation
  5. Long chain Interest modeling
  6. Long chain Selection algorithm
  7. Long chain Interest Encoder
  8. Neighbor Interest Encoder
  9. Collaborative Interest Fusion and user representation
  10. Candidate News Modeling and Prediction
  11. Experiment Setup
  12. Dataset and Experiment Settings
  13. Comparison Methods
  14. Experiment Results and Analysis
  15. Main Comparison Results
  16. ...and 8 more sections

Figures (5)

  • Figure 1: An example of some news click global graph with traditional limited hop modeling without long chain selection and utilization.
  • Figure 2: The overall architecture of our model. The graph construction is based on the user click history.
  • Figure 3: Results of different module variants.
  • Figure 4: Impact of different hops
  • Figure 5: Comparison of the effect of GloCIM and GLORY in utilizing global click graph for news recommendation. The circled red numbers represent different selected hop, and numbers on the arrows represent the accumulated frequency. The red numbers in the news represent the similarity to the user click news selected. The diamond icon represents the news that was actually clicked.