Filters








279 Hits in 4.5 sec

Network Embedding For Link Prediction in Bipartite Networks

Özge KART
2021 European Journal of Science and Technology  
The experiments performed on two bipartite social networks built from public datasets led promising results with 0.939 and 0.974 AUC values.  ...  Many social networks have a bipartite nature. Link prediction in social networks has been the focus of interest for many researchers recently.  ...  Network embedding methods node2vec and BiNe are applied on bipartite social networks to solve the link prediction problem.  ... 
doi:10.31590/ejosat.937722 fatcat:fgl3ran6lzdfxps3guzuqddu2i

Applying Graph Convolution Networks to Recommender Systems based on graph topology

Alper ÖZCAN
2022 DÜMF Mühendislik Dergisi  
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.  ...  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  ...  The main contributions of this paper are three-fold: • We propose a GCN-based architecture for recommender systems to learn graph topology of users and items in bipartite network settings • Local measures  ... 
doi:10.24012/dumf.1081137 fatcat:6v7mnjkuijc4zezzbdtlaedlpm

Revisiting Graph based Social Recommendation: A Distillation Enhanced Social Graph Network

Ye Tao, Ying Li, Su Zhang, Zhirong Hou, Zhonghai Wu
2022 Proceedings of the ACM Web Conference 2022  
Social recommendation, which leverages social connections to construct Recommender Systems (RS), plays an important role in alleviating information overload.  ...  Based on these analyses, we propose a Distillation Enhanced SocIal Graph Network (DESIGN).  ...  DANSER [42] uses a dual graph attention network to collaboratively learn representations for two-fold social effects.  ... 
doi:10.1145/3485447.3512003 fatcat:brju3ncfyjfk7l5on4glo2ftxa

Movie rating prediction using content-based and link stream features [article]

Tiphaine Viard, Raphaël Fournier-S'niehotta
2018 arXiv   pre-print
Focusing on a traditional recommender system context, the rating prediction on the MovieLens20M dataset, we input these features along with some content-based ones into a gradient boosting machine (XGBoost  ...  While graph-based collaborative filtering recommender systems have been introduced several years ago, there are still several shortcomings to deal with, the temporal information being one of the most important  ...  While finding similar users and grouping them into communities is a vast subject in social network analysis, it has been attempted with limited success in the recommendation context.  ... 
arXiv:1805.02893v1 fatcat:qb3zznrhvbbarn6pjttdfqmvfi

Optimizing Parallel Collaborative Filtering Approaches for Improving Recommendation Systems Performance

Christos Sardianos, Grigorios Ballas Papadatos, Iraklis Varlamis
2019 Information  
, from commercial e-shops to social networks and product review sites.  ...  We evaluated the proposed approach on a bipartite product-rating network using an implementation on Apache Spark.  ...  density in each partition and boost the performance of the SVD++ algorithm, even for partitions with only one rating.  ... 
doi:10.3390/info10050155 fatcat:ki6shksnebdgrefiavmdopasty

An Enhanced Neural Graph based Collaborative Filtering with Item Knowledge Graph

Sangeetha M., Meera Devi Thiagarajan
2022 International Journal of Computers Communications & Control  
Then, the embedding layer will process on both the recommendations to provide a higher order relation between the users and items.  ...  Recommendation system is a process of filtering information to retain buyers on e-commerce sites or applications. It is used on all e-commerce sites, social media platform and multimedia platform.  ...  Because, adding more embedding layer may results in overfitting. Analysis based on N-fold The term N-fold is used to split the adjoint matrix for the message propagation function.  ... 
doi:10.15837/ijccc.2022.4.4568 fatcat:b6dqcrnl3ndkff457vhidar3b4

SiReN: Sign-Aware Recommendation Using Graph Neural Networks [article]

Changwon Seo, Kyeong-Joong Jeong, Sungsu Lim, Won-Yong Shin
2022 arXiv   pre-print
In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy.  ...  Specifically, SiReN has three key components: 1) constructing a signed bipartite graph for more precisely representing users' preferences, which is split into two edge-disjoint graphs with positive and  ...  Network Model and Basic Settings In recommender systems, the basic input is the historical user-item interactions with ratings, which is represented as a weighted bipartite graph.  ... 
arXiv:2108.08735v2 fatcat:bd2rfl4pbbc35aj5uapy2cdhj4

Semantic embedding for regions of interest

Debjyoti Paul, Feifei Li, Jeff M. Phillips
2021 The VLDB journal  
All sources interplay with each other, and together build a more complete picture of the spatial and social dynamics at play in a region.  ...  Applications like popularity region prediction demonstrate the benefit of using ROI embedding as features in comparison with baselines.  ...  [4] to our notice, which explores folded bipartite network embedding using graph convolution network (GCN).  ... 
doi:10.1007/s00778-020-00647-0 fatcat:yqh7i353zrhpziztuciy5v7qua

Progresses and Challenges in Link Prediction [article]

Tao Zhou
2021 arXiv   pre-print
embedding, matrix completion, ensemble learning and others, mainly extracted from thousands of related publications in the last decade.  ...  Link prediction is a paradigmatic problem in network science, which aims at estimating the existence likelihoods of nonobserved links, based on known topology.  ...  social networks.  ... 
arXiv:2102.11472v2 fatcat:jnqxnuhc6vg4fosuekoghkjqwa

Towards an Adaptive Skip-gram Model for Network Representation Learning

I-Chung Hsieh, Cheng-Te Li
2022 IEEE Access  
Based on benchmark datasets with three citation networks and three social networks, we demonstrate the improvement of our ASK model for network representation learning in tasks of link prediction, node  ...  classification, and embedding visualization.  ...  In the recommender systems with user attributes and their interactions with items, to learn essential features, GNN-SoR [5] generates the embeddings based on social influence and user The associate editor  ... 
doi:10.1109/access.2022.3164670 fatcat:3doknonthfecpev6un7ydwlpxy

SHINE

Hongwei Wang, Fuzheng Zhang, Min Hou, Xing Xie, Minyi Guo, Qi Liu
2018 Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining - WSDM '18  
Then we propose a novel and flexible end-to-end Signed Heterogeneous Information Network Embedding (SHINE) framework to extract users' latent representations from heterogeneous networks and predict the  ...  In online social networks people often express attitudes towards others, which forms massive sentiment links among users.  ...  , and [34] proves that information from knowledge base could boost the performance of recommendation.  ... 
doi:10.1145/3159652.3159666 dblp:conf/wsdm/WangZHXGL18 fatcat:e3laxfmje5d5jplrvrjevhctdu

A Practical Two-stage Ranking Framework for Cross-market Recommendation [article]

Zeyuan Chen, He Wang, Xiangyu Zhu, Haiyan Wu, Congcong Gu, Shumeng Liu, Jinchao Huang, Wei Zhang
2022 arXiv   pre-print
models (Graph Neural Network, DeepWalk, etc.) and traditional recommendation models (ItemCF, UserCF, Swing, etc.).  ...  Cross-market recommendation aims to recommend products to users in a resource-scarce target market by leveraging user behaviors from similar rich-resource markets, which is crucial for E-commerce companies  ...  ACKNOWLEDGMENTS We thank everyone associated with organizing and sponsoring the WSDM Cup 2022.  ... 
arXiv:2204.12682v1 fatcat:applr5ojw5f4rpukrwi5zodxzi

Semantic Annotation for Places in LBSN through Graph Embedding

Yan Wang, Zongxu Qin, Jun Pang, Yang Zhang, Jin Xin
2017 Proceedings of the 2017 ACM on Conference on Information and Knowledge Management - CIKM '17  
With the prevalence of location-based social networks (LBSNs), automated semantic annotation for places plays a critical role in many LBSN-related applications.  ...  For observed patterns, a place-temporal bipartite graph is used to further adjust place embeddings by reducing unsupervised loss.  ...  The prediction is performed with the SVM classifier and based on 10-fold cross-validation.  ... 
doi:10.1145/3132847.3133075 dblp:conf/cikm/WangQPZX17 fatcat:47bjvwuufrbkderoolnd55jqjq

Query suggestion using hitting time

Qiaozhu Mei, Dengyong Zhou, Kenneth Church
2008 Proceeding of the 17th ACM conference on Information and knowledge mining - CIKM '08  
In this work, we propose a novel query suggestion algorithm based on ranking queries with the hitting time on a large scale bipartite graph.  ...  The proposed algorithm and its variations can successfully boost long tail queries, accommodating personalized query suggestion, as well as finding related authors in research.  ...  Indeed, with the notion introduced in Section 2, we can fold a bipartite graph into a graph with only one group of vertices, but with a different weighing function for the folded edges.  ... 
doi:10.1145/1458082.1458145 dblp:conf/cikm/MeiZC08 fatcat:fxzg6tpu35czxe4is5byo7r4ma

Temporal Collaborative Filtering with Graph Convolutional Neural Networks [article]

Esther Rodrigo Bonet, Duc Minh Nguyen, Nikos Deligiannis
2020 arXiv   pre-print
Temporal collaborative filtering (TCF) methods aim at modelling non-static aspects behind recommender systems, such as the dynamics in users' preferences and social trends around items.  ...  Recently, graph-neural-network-based (GNN-based) approaches have shown improved performance in providing accurate recommendations over traditional MF-based approaches in non-temporal CF settings.  ...  Recommender systems can be formulated as a link prediction problem by representing users, items and their interactions in a bipartite graph.  ... 
arXiv:2010.06425v1 fatcat:gvuwjbqtdveitpx6exdxa352ay
« Previous Showing results 1 — 15 out of 279 results