Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model

By Binbin Hu, Chuan Shi, Wayne Xin Zhao, Philip S. Yu. Knowledge Discovery and Data Mining, 2018

706 citations recorded by the source corpus.

Heterogeneous information network (HIN) has been widely adopted in recommender systems due to its excellence in modeling complex context information. Although existing HIN based recommendation methods have achieved performance improvement to some extent, they have two major shortcomings. First, these models seldom learn an explicit representation for path or meta-path in the recommendation task. Second, they do not consider the mutual effect between the meta-path and the involved user-item pair in an interaction. To address these issues, we develop a novel deep neural network with the co-attention mechanism for leveraging rich meta-path based context for top-N recommendation. We elaborately design a three-way neural interaction model by explicitly incorporating meta-path based context. To construct the meta-path based context, we propose to use a priority based sampling technique to select high-quality path instances. Our model is able to learn effective representations for users, items and meta-path based context for implementing a powerful interaction function. The co-attention mechanism improves the representations for meta-path based con- text, users and items in a mutual enhancement way. Extensive experiments on three real-world datasets have demonstrated the effectiveness of the proposed model. In particular, the proposed model performs well in the cold-start scenario and has potentially good interpretability for the recommendation results.

Subfields: Artificial Intelligence, Computer Networks and Communications, Information Systems

View Paper: https://www.semanticscholar.org/paper/0cfac458b176a1e81879aff4344c5278114cc171

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

In Computer Networks and Communications

In Information Systems

Citations in the corpus

Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems (2019, methodology): “(2) Path-based methods [8, 33, 36] explore various patterns of connections among items in a KG (a.”
Neural Collaborative Filtering vs. Matrix Factorization Revisited (2020, methodology): “Most commonly, a multilayer perceptron (MLP) is used for the network architecture (e.g. [18, 37, 38, 20, 32, 27]).”
Heterogeneous Graph Neural Network (2019, background): “This ubiquity of HetG has led to an influx of research on corresponding graph mining methods and algorithms such as relation inference [2, 25, 33, 35], personalized recommendation [10, 23], node classification [36], etc .”
Are we really making much progress? A worrying analysis of recent neural recommendation approaches (2019, neutral): “We optimized our baselines for Precision, as was apparently done in [17].”
Advances and Challenges in Conversational Recommender Systems: A Survey (2021, background): “Recently, it has become common for researchers to speed up evaluation by sampling a small set of of irrelevant items and calculate the ranking-based metrics only on the small set [60, 44, 64, 194].”
Knowledge Graph Contrastive Learning for Recommendation (2022, methodology): “For instance, MCRec [13] designs meta-path-based mutual attention mechanism for Top-N recommendation, which produces user, item, and meta-path-based context representations.”
Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation (2020, methodology): “3403207 1 INTRODUCTION Recommender systems [3, 11, 31] have been widely deployed in various online services, such as E-commerce platforms and news portals, to address the issue of information overload for users.”
On Sampled Metrics for Item Recommendation (2020, methodology): “,m = 100 samples for datasets with n = {4k, 10k, 17k, 140k, 2M} items [7, 9, 15],m = 50 samples for n ∈ {2k, 18k, 14k} items [10], or m = 200 samples for n ∈ {17k, 450k} items [17].”
Neural Input Search for Large Scale Recommendation Models (2019, methodology): “We formulate a movie recommendation problem by following a widely adapted experiment setting [10, 11, 26]: User ratings are treated as implicit feedback, i.”
Learning Intents behind Interactions with Knowledge Graph for Recommendation (2021, background): “GNN-based Methods [17, 38, 39, 41, 47] are founded upon the information aggregation mechanism of graph neural networks (GNNs) [13, 14, 19, 34, 42].”
Recommendation system based on deep learning methods: a systematic review and new directions (2019, methodology): “Hu et al. (2018) designed a three-way neural interaction model using CNN model by incorporating meta-path-based context.”
Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation (2019, methodology): “Some previous work has introduced the connectivity patterns into recomendation sys-tem [5, 7, 10, 18–20 , 28 ].”
Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation (2019, methodology): “[13] also utilizes attention mechanism to conduct the meta-path based recommendation.”
A Survey on Knowledge Graph-Based Recommender Systems (2020, methodology): “Some papers [1], [79], [82] build the user-item graph by directly leveraging the interaction data and attributes of movies inside the MovieLens dataset or the DoubanMovie dataset, while others [66], [75], [76], [77], [80], [81], [83], [86], [87], [96] still utilize external database to enrich the…”