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.
BibTeX
@inproceedings{mao-etal-2022-digat,
title = "{DIGAT}: Modeling News Recommendation with Dual-Graph Interaction",
author = "Mao, Zhiming and
Li, Jian and
Wang, Hongru and
Zeng, Xingshan and
Wong, Kam-Fai",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.491/",
doi = "10.18653/v1/2022.findings-emnlp.491",
pages = "6595--6607"
}