DIGAT: Modeling News Recommendation with Dual-Graph Interaction

Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, Kam-Fai Wong


Abstract
News recommendation (NR) is essential for online news services. Existing NR methods typically adopt a news-user representation learning framework, facing two potential limitations. First, in news encoder, single candidate news encoding suffers from an insufficient semantic information problem. Second, existing graph-based NR methods are promising but lack effective news-user feature interaction, rendering the graph-based recommendation suboptimal. To overcome these limitations, we propose dual-interactive graph attention networks (DIGAT) consisting of news- and user-graph channels. In the news-graph channel, we enrich the semantics of single candidate news by incorporating the semantically relevant news information with a semantic-augmented graph (SAG). In the user-graph channel, multi-level user interests are represented with a news-topic graph. Most notably, we design a dual-graph interaction process to perform effective feature interaction between the news and user graphs, which facilitates accurate news-user representation matching. Experiment results on the benchmark dataset MIND show that DIGAT outperforms existing news recommendation methods. Further ablation studies and analyses validate the effectiveness of (1) semantic-augmented news graph modeling and (2) dual-graph interaction.
Anthology ID:
2022.findings-emnlp.491
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6595–6607
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.491
DOI:
10.18653/v1/2022.findings-emnlp.491
Bibkey:
Cite (ACL):
Zhiming Mao, Jian Li, Hongru Wang, Xingshan Zeng, and Kam-Fai Wong. 2022. DIGAT: Modeling News Recommendation with Dual-Graph Interaction. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 6595–6607, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
DIGAT: Modeling News Recommendation with Dual-Graph Interaction (Mao et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.491.pdf