Filters








8,281 Hits in 6.6 sec

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph [article]

Jiarui Jin, Jiarui Qin, Yuchen Fang, Kounianhua Du, Weinan Zhang, Yong Yu, Zheng Zhang, Alexander J. Smola
2020 arXiv   pre-print
In this paper, we propose an end-to-end Neighborhood-based Interaction Model for Recommendation (NIRec) to address the above problems.  ...  To the best of our knowledge, this is the first work providing an efficient neighborhood-based interaction model in the HIN-based recommendations.  ...  In this work, our propose is not only to deliver graph representation learning techniques on heterogeneous graph, but also propose a novel efficient neighborhood-based interaction methods, which should  ... 
arXiv:2007.00216v1 fatcat:cruhwo3hdzdmpe5v3cvdboafaa

GraphHINGE: Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network [article]

Jiarui Jin, Kounianhua Du, Weinan Zhang, Jiarui Qin, Yuchen Fang, Yong Yu, Zheng Zhang, Alexander J. Smola
2021 arXiv   pre-print
Specifically, we first introduce Neighborhood-based Interaction (NI) module to model the interactive patterns under the same metapaths, and then extend it to Cross Neighborhood-based Interaction (CNI)  ...  Recent attempts either rely on explicit path reachability to leverage path-based semantic relatedness or graph neighborhood to learn heterogeneous network representations before predictions.  ...  'An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph'.  ... 
arXiv:2011.12683v2 fatcat:nv27cwdpkrblto3fja7wqdnhdy

Single-Layer Graph Convolutional Networks For Recommendation [article]

Yue Xu and Hao Chen and Zengde Deng and Junxiong Zhu and Yanghua Li and Peng He and Wenyao Gao and Wenjun Xu
2020 arXiv   pre-print
Graph Convolutional Networks (GCNs) and their variants have received significant attention and achieved start-of-the-art performances on various recommendation tasks.  ...  Though effective, the excessive amount of model parameters largely hinder their applications in real-world recommender systems.  ...  On the other hand, the heterogeneous graph can be modeled as a heterogeneous information network (HIN), which is defined as follows: Definition 3.1 (Heterogeneous Information Network).  ... 
arXiv:2006.04164v1 fatcat:7qrn4wi35jhqtgb7tqyzipdj7i

Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation [article]

Kyung-Min Kim, Donghyun Kwak, Hanock Kwak, Young-Jin Park, Sangkwon Sim, Jae-Han Cho, Minkyu Kim, Jihun Kwon, Nako Sung, Jung-Woo Ha
2019 arXiv   pre-print
The oversmoothing of GNNs is an obstacle of GNN-based social recommendation as well. Here we propose a new graph embedding method Heterogeneous Graph Propagation (HGP) to tackle these issues.  ...  However, various challenging issues of social graphs hinder the practical usage of GNNs for social recommendation, such as their complex noisy connections and high heterogeneity.  ...  ACKNOWLEDGMENTS The authors appreciate Andy Ko for insightful comments and discussion.  ... 
arXiv:1908.02569v1 fatcat:br7cbjrybzat7o7sr2zuvryf5y

Position-enhanced and Time-aware Graph Convolutional Network for Sequential Recommendations

Liwei Huang, Yutao Ma, Yanbo Liu, Bohong Danny Du, Shuliang Wang, Deyi Li
2022 ACM Transactions on Information Systems  
To address the above problems, in this article, we attempt to model user-item interactions by a bipartite graph structure and propose a new recommendation approach based on a P osition-enhanced and T ime-aware  ...  In particular, it can make a better trade-off between recommendation performance and model training efficiency, which holds great potential for online session-based recommendation scenarios in the future  ...  In addition to hypergraphs, researchers have proposed sequential recommendation models based on other types of graphs, such as tripartite graphs [19] and heterogeneous interaction graphs [47] , to capture  ... 
doi:10.1145/3511700 fatcat:5jbvfmzbqng7lcegj5eeqk33uu

ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest [article]

Yuezihan Jiang, Yu Cheng, Hanyu Zhao, Wentao Zhang, Xupeng Miao, Yu He, Liang Wang, Zhi Yang, Bin Cui
2022 arXiv   pre-print
We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs.  ...  ZOOMER is designed for tackling two challenges presented by the massive user data at Taobao: low training/serving efficiency due to the huge scale of the graphs, and low recommendation quality due to the  ...  ACKNOWLEDGMENTS We thank the anonymous reviewers for their valuable suggestions. This work is supported by NSFC (No. 61832001, 61972004), Beijing Academy of Artificial Intelligence (BAAI) and Alibaba.  ... 
arXiv:2203.12596v1 fatcat:azfdiue4evh3lmocvvrjq45g2i

Graph4Rec: A Universal Toolkit with Graph Neural Networks for Recommender Systems [article]

Weibin Li, Mingkai He, Zhengjie Huang, Xianming Wang, Shikun Feng, Weiyue Su, Yu Sun
2021 arXiv   pre-print
Finally, we investigate methods including negative sampling, ego graph construction order, and warm start strategy to find a more effective and efficient GNNs practice on recommender systems.  ...  However, many recent publications using GNNs for recommender systems cannot be directly compared, due to their difference on datasets and evaluation metrics.  ...  For example, user-based collaborative filtering methods can predict the likely-to-interact items for a user based on ratings given to that item by the other users with similar tastes, which are measured  ... 
arXiv:2112.01035v2 fatcat:2wjlfc75xfh7zlus3swh25sqf4

MultiBiSage: A Web-Scale Recommendation System Using Multiple Bipartite Graphs at Pinterest [article]

Saket Gurukar, Nikil Pancha, Andrew Zhai, Eric Kim, Samson Hu, Srinivasan Parthasarathy, Charles Rosenberg, Jure Leskovec
2022 arXiv   pre-print
These embeddings can then be used for several tasks such as recommendation and search.  ...  To that end, we model the diverse entities and their diverse interactions through multiple bipartite graphs and propose a novel data-efficient MultiBiSage model.  ...  Moreover, these entities can have diverse interactions on Pinterest. Figure 1 shows an example heterogeneous graph at Pinterest.  ... 
arXiv:2205.10666v1 fatcat:3pf3hwzyc5hubfqjqifmefh2zy

Graph Learning Approaches to Recommender Systems: A Review [article]

Shoujin Wang, Liang Hu, Yan Wang, Xiangnan He, Quan Z. Sheng, Mehmet Orgun, Longbing Cao, Nan Wang, Francesco Ricci, Philip S. Yu
2020 arXiv   pre-print
GLRS mainly employ the advanced graph learning approaches to model users' preferences and intentions as well as items' characteristics and popularity for Recommender Systems (RS).  ...  In this paper, we provide a systematic review of GLRS, on how they obtain the knowledge from graphs to improve the accuracy, reliability and explainability for recommendations.  ...  Accordingly, multiple heterogeneous graphs are jointly built for recommendations: the user-item interaction based bipartite graphs providing the key information for modeling user choices, user attributed  ... 
arXiv:2004.11718v1 fatcat:w6ug72c4pvgoxjcf643tmddfii

Visualization and Analysis Model of Industrial Economy Status and Development Based on Knowledge Graph and Deep Neural Network

Jing Quan, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
The framework achieves modeling and integration of knowledge graph neighborhood information from breadth dimension and depth dimension to realize personalized recommendation sorting and improves the F1  ...  A framework of breadth and depth recommendation ranking based on a knowledge graph is proposed and implemented. This paper provides a visual analysis method to sort and classify multivariate data.  ...  and interaction between different neighborhoods of the knowledge graph, we propose and implement a recommendation ranking framework based on the breadth and depth of the knowledge graph, which achieves  ... 
doi:10.1155/2022/7008093 pmid:35528336 pmcid:PMC9071965 fatcat:h6d3ty5rcbb3jp4na5tsopi34e

Graph Neural Networks in Recommender Systems: A Survey [article]

Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui
2022 arXiv   pre-print
Specifically, we provide a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks.  ...  This article aims to provide a comprehensive review of recent research efforts on GNN-based recommender systems.  ...  The performance of the model depends on the sampling strategy and the more efficient sampling strategy for neighborhood construction deserves further studying.  ... 
arXiv:2011.02260v4 fatcat:hvk22yyid5bzjnzmzchyti25ja

An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation [article]

Yanru Qu, Ting Bai, Weinan Zhang, Jianyun Nie, Jian Tang
2020 arXiv   pre-print
We reveal an early summarization problem in existing graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between user-side and item-side) distinctively.  ...  This paper studies graph-based recommendation, where an interaction graph is constructed from historical records and is lever-aged to alleviate data sparsity and cold start problems.  ...  The final model, called Knowledgeenhanced Neighborhood Interaction (KNI), is evaluated on 4 realworld datasets and compared with 8 feature-based, meta path-based, and graph-based models.  ... 
arXiv:1908.04032v2 fatcat:ujccm4mxvre2pcx7yazfpyodsu

Applying Graph Convolution Networks to Recommender Systems based on graph topology

Alper ÖZCAN
2022 DÜMF Mühendislik Dergisi  
Recently, graph representation learning methods based on node embedding have drawn attention in Recommender systems such as Graph Convolutional Networks (GCNs) that is powerful method for collaborative  ...  In this paper, we propose a recommendation algorithm based on node similarity convolutional matrices with topological property in GCNs where the linkage measure is illustrated as a bipartite graph.  ...  Generally, the graph-based models are used in heterogeneous networks in which the data is more complex.  ... 
doi:10.24012/dumf.1081137 fatcat:6v7mnjkuijc4zezzbdtlaedlpm

Group-Buying Recommendation for Social E-Commerce [article]

Jun Zhang, Chen Gao, Depeng Jin, Yong Li
2020 arXiv   pre-print
However, designing a personalized recommendation model for group buying is an entirely new problem that is seldom explored.  ...  Group-buying recommendation for social e-commerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales.  ...  Social Influence-based Group Recommender (SIGR) is composed of a bipartite graph embedding model that leverages user-item graph and group-item graph and an attention mechanism used for learning user social  ... 
arXiv:2010.06848v2 fatcat:ewdu4gbz7zed3pwfzd3mybqwee

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang
2021 IEEE Transactions on Knowledge and Data Engineering  
Experiments on three real-world heterogeneous graphs have further validated the efficacy of WIDEN on both transductive and inductive node representation learning, as well as the superior training efficiency  ...  However, a majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs with various types of nodes and edges.  ...  For instance, when learning a user's preference for recommendation, all her/his interacted item nodes carry strong indicative signals on the user's personal interests.  ... 
doi:10.1109/tkde.2021.3100529 fatcat:azur4cdwafg3zhk27tnssqysza
« Previous Showing results 1 — 15 out of 8,281 results