Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation

By Shaohua Fan, Junxiong Zhu, Xiaotian Han, Chuan Shi, Linmei Hu, Biyu Ma, Yongliang Li. Knowledge Discovery and Data Mining, 2019

389 citations recorded by the source corpus.

With the prevalence of mobile e-commerce nowadays, a new type of recommendation services, called intent recommendation, is widely used in many mobile e-commerce Apps, such as Taobao and Amazon. Different from traditional query recommendation and item recommendation, intent recommendation is to automatically recommend user intent according to user historical behaviors without any input when users open the App. Intent recommendation becomes very popular in the past two years, because of revealing user latent intents and avoiding tedious input in mobile phones. Existing methods used in industry usually need laboring feature engineering. Moreover, they only utilize attribute and statistic information of users and queries, and fail to take full advantage of rich interaction information in intent recommendation, which may result in limited performances. In this paper, we propose to model the complex objects and rich interactions in intent recommendation as a Heterogeneous Information Network. Furthermore, we present a novel M etapath-guided E mbedding method for I ntent Rec ommendation~(called MEIRec). In order to fully utilize rich structural information, we design a metapath-guided heterogeneous Graph Neural Network to learn the embeddings of objects in intent recommendation. In addition, in order to alleviate huge learning parameters in embeddings, we propose a uniform term embedding mechanism, in which embeddings of objects are made up with the same term embedding space. Offline experiments on real large-scale data show the superior performance of the proposed MEIRec, compared to representative methods.Moreover, the results of online experiments on Taobao e-commerce platform show that MEIRec not only gains a performance improvement of 1.54% on CTR metric, but also attracts up to 2.66% of new users to search queries.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/025ea689e6ab3b544101df17233e87536a1e578a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiangnan He
2. Xiang Wang
3. Liqiang Nie
4. Chuan Shi
5. Yong Li
6. Meng Wang
7. Chen Gao
8. Tat-seng Chua

In Information Systems

1. Xiangnan He
2. Xiang Wang
3. Liqiang Nie
4. Meng Wang
5. Yong Li
6. Chen Gao
7. Le Wu
8. Tat-seng Chua

Citations in the corpus

• A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, neutral): “With the development of embedding technology, matrix factorization [84], [85], [86], random walk [2] and advanced neural networks [3], [87], [88], [89], [20], [19] are proposed to learn embeddings of user and item, so as to capture the complex interactions.”
• Are we really making much progress?: Revisiting, benchmarking and refining heterogeneous graph neural networks (2021, background): “Recommendation is a main application for Heterogeneous GNNs, but most related works [9, 10, 24, 25] only focus on their specific industrial data, resulting in non-open datasets and limited transferability of the models.”
• Heterogeneous Graph Structure Learning for Graph Neural Networks (2021, methodology): “…graph data, has drawn increasing attention and is widely applied to node classification (Kipf and Welling 2017; Velickovic et al. 2018; Xu et al. 2019), graph classification (Duvenaud et al. 2015; Lee, Lee, and Kang 2019), and recommendation (Ying et al. 2018; Fan et al. 2019b; Wang et al. 2019a).”
• A Survey on Accuracy-Oriented Neural Recommendation: From Collaborative Filtering to Information-Rich Recommendation (2021, background): “Recently, researchers proposed to leverage word embedding techniques for better content recommendation [69], [82], [83], [84], [85], [86], [87], [88].”
• Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning (2021, neutral): “, recommender [5] and security system [6].”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, background): “Specifically, the utilization of knowledge graph with GNN significantly addresses some practical issues in recommender systems [53], for example, cold start problem [42, 232] and dynamicity [163].”
• Interest-aware Message-Passing GCN for Recommendation (2021, methodology): “…items; PinSage [43] combines random walks with multiple graph convolution layers on the item-item graph for Pinterest image recommendation; MEIRec [8] utilizes metapath-guided neighbors to exploit rich structure information for intent recommendation; NGCF [33] exploits high-order proximity by…”
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems (2020, background): “Another line of work deals with the complex and heterogeneous interaction types between user and item in large-scale e-commerce networks [2, 4].”