26,214 Hits in 3.3 sec

Relation-aware Heterogeneous Graph for User Profiling [article]

Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang
2021 pre-print
To solve these issues, we propose to leverage the relation-aware heterogeneous graph method for user profiling, which also allows capturing significant meta relations.  ...  Via such interactions on different relation types, our model can generate representations with rich information for the user profile prediction.  ...  To that end, we propose Relationaware Heterogeneous Graph Network for user profiling (RHGN) that can model multiple relations on the heterogeneous graph.  ... 
doi:10.1145/3459637.3482170 arXiv:2110.07181v1 fatcat:vf2woqt2rrfplodka6rlj34eba

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
The objective of this task is to map heterogeneous relational data into latent representation space, such that the structural and relational properties from both user and item domain can be well preserved  ...  We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.  ...  In addition, graph neural networks have been utilized for encoding the knowledge-aware relations to transform the knowledge graph into user interest modeling, such as KGNN-LS [Wang and others, 2019] and  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

ATBRG: Adaptive Target-Behavior Relational Graph Network for Effective Recommendation [article]

Yufei Feng, Binbin Hu, Fuyu Lv, Qingwen Liu, Zhiqiang Zhang, Wenwu Ou
2020 arXiv   pre-print
In this work, we propose a new framework named Adaptive Target-Behavior Relational Graph network (ATBRG for short) to effectively capture structural relations of target user-item pairs over KG.  ...  Existing methods either explore independent meta-paths for user-item pairs over KG, or employ graph neural network (GNN) on whole KG to produce representations for users and items separately.  ...  Until now, given a target user-item pair ⟨u, i⟩, we have the profile embeddings for user u and item i, and knowledge aware embedding from adaptive target-behavior relational graph for user behaviors and  ... 
arXiv:2005.12002v1 fatcat:uvjxqnmtdfhchcjhjncifyijge

QoS-aware middleware for ubiquitous and heterogeneous environments

K. Nahrstedt, Dongyan Xu, D. Wichadakul, Baochun Li
2001 IEEE Communications Magazine  
Middleware systems have emerged in recent years to support applications in heterogeneous and ubiquitous computing environments.  ...  QOS-AWARE MIDDLEWARE ARCHITECTURE Our QoS-aware middleware architecture favors applications modeled by a generic application component model.  ...  ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their valuable comments on this article.  ... 
doi:10.1109/35.965372 fatcat:kskzrwqisrexhlp4xhrvwufhmu

UPRec: User-Aware Pre-training for Recommender Systems [article]

Chaojun Xiao, Ruobing Xie, Yuan Yao, Zhiyuan Liu, Maosong Sun, Xu Zhang, Leyu Lin
2021 arXiv   pre-print
In this paper, we propose a method to enhance pre-trained models with heterogeneous user information, called User-aware Pre-training for Recommendation (UPRec).  ...  Specifically, UPRec leverages the user attributes andstructured social graphs to construct self-supervised objectives in the pre-training stage and proposes two user-aware pre-training tasks.  ...  In our model, we propose two novel user-aware tasks, including user attribute prediction and social relation detection, which are designed to utilize user attributes and social graphs.  ... 
arXiv:2102.10989v1 fatcat:fsur7dod6vcurlauxqxtlkbosi


Abhijith Kashyap, Reza Amini, Vagelis Hristidis
2012 Proceedings of the 21st ACM international conference on Information and knowledge management - CIKM '12  
Intuitively, users in the same group may have similar relevance judgments for queries related to these groups.  ...  SonetRank builds and maintains a rich graph-based model, termed Social Aware Search Graph, consisting of groups, users, queries and results click-through information.  ...  For example, if the SAS Graph contains groups and queries related to City of Hope and Leukemia as in the example from Section 1, and a user executes a query related to movies (e.g.  ... 
doi:10.1145/2396761.2398569 dblp:conf/cikm/KashyapAH12 fatcat:yoxugpz22zgzbf2zedu5zk5wq4

Price-aware Recommendation with Graph Convolutional Networks [article]

Yu Zheng, Chen Gao, Xiangnan He, Yong Li, Depeng Jin
2020 arXiv   pre-print
Further analysis reveals that modeling the price awareness is particularly useful for predicting user preference on items of unexplored categories.  ...  For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions.  ...  PUP to maximize the revenue is an interesting and important research question which extends price-aware recommendation to value-aware recommendation.  ... 
arXiv:2003.03975v1 fatcat:s67v6cqifjbnzpzqznm6nhdgoe

DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction [article]

Yule Wang, Qiang Luo, Yue Ding, Dong Wang, Hongbo Deng
2021 arXiv   pre-print
To be specific, we first consider various dependency types between item nodes and perform dependency-aware heterogeneous attention for denoising and obtaining accurate sequence item representations.  ...  Secondly, for multiple interests extraction, multi-head attention is conducted on top of the graph embedding.  ...  havior sequence, we perform multi-dependency-aware heterogeneous attention and self-supervised interest learning.  ... 
arXiv:2109.12512v1 fatcat:vznmni5xfzhsnjkfnxh5kfyhsa

Multi-Behavior Sequential Recommendation with Temporal Graph Transformer

Lianghao Xia, Chao Huang, Yong Xu, Jian Pei
2022 IEEE Transactions on Knowledge and Data Engineering  
In this work, we tackle the dynamic user-item relation learning with the awareness of multi-behavior interactive patterns.  ...  The new TGT method endows the sequential recommendation architecture to distill dedicated knowledge for type-specific behavior relational context and the implicit behavior dependencies.  ...  ACKNOWLEDGMENTS We thank the reviewers for their valuable feedback and comments. This  ... 
doi:10.1109/tkde.2022.3175094 fatcat:iqreqptfvbeeffmit4isv7xsuu

Adaptive Alleviation for Popularity Bias in Recommender Systems with Knowledge Graph

Feng Wei, Shuyu Chen, Jie Jin, Shuai Zhang, Hongwei Zhou, Yingbo Wu
2022 Security and Communication Networks  
Concretely, we explore fine-grained preferences (including popularity preference) behind a user-item interaction by using the heterogeneous graph transformer over the knowledge graph embedded with popularity  ...  In this work, we propose a novel debias framework with knowledge graph (AWING), which adaptively alleviates popularity bias from the users' perspective.  ...  modeling, which uses multiple preferences to profile user-item relationships and aligns each preference with the relation in knowledge graph embed with popularity nodes; (3) heterogeneous graph transformer  ... 
doi:10.1155/2022/4264489 doaj:d10ee085cd804d81ba21297d19716770 fatcat:jrsmvuomhndqjaj6365emppco4

Recurring Retrieval Needs in Diverse and Dynamic Dataspaces: Issues and Reference Framework

Barbara Catania, Francesco De Fino, Giovanna Guerrini
2017 International Conference on Extending Database Technology  
In this paper, referring to a graph-based modeling of dataspaces and requests, we propose a preliminary approach in this direction centered on the enabling concept of Profiled Graph Query Pattern (PGQP  ...  Processing information requests over heterogeneous dataspaces is very challenging because aimed at guaranteeing user satisfaction with respect to conflicting requirements on result quality and response  ...  In [3] , to overcome difficulties related to heterogeneity and dynamic nature, the exploitation of additional information, in terms of user profile and request context, data and processing quality, similar  ... 
dblp:conf/edbt/CataniaFG17 fatcat:vacnfgwpn5amxcq6xtaspxymaa

Feature-rich networks: going beyond complex network topologies

Roberto Interdonato, Martin Atzmueller, Sabrina Gaito, Rushed Kanawati, Christine Largeron, Alessandra Sala
2019 Applied Network Science  
Attributed Graphs, Heterogeneous Networks, Multilayer Networks, Temporal Networks, Location-aware Networks, Knowledge Networks, Probabilistic Networks, and many other task-driven and data-driven models  ...  The growing availability of multirelational data gives rise to an opportunity for novel characterization of complex real-world relations, supporting the proliferation of diverse network models such as  ...  Definition 11 (User-user graph) A user-user graph G = (V , E) is a graph where nodes in V represent users and directed edges in E ⊆ V × V represent relations between users.  ... 
doi:10.1007/s41109-019-0111-x fatcat:obdhovj2kffqbe6drixhw3bp5q

Guest editorial: web information technologies

Xuemin Lin, Jeffrey Xu Yu
2015 World wide web (Bussum)  
Huang et al. study user attribute identification or profile inference in the third paper, "A multi-source integration framework for user occupation inference in social media systems".  ...  The first paper, by Huang et al, "Mining streams of short text for analysis of world-wide event evolutions", addresses the limitations of existing techniques such as LDA in detecting and tracking events  ...  In the fourth paper, "User communities evolution in microblogs: A public awareness barometer for real world events", Giatsoglou, Chatzakou and Vakali study the problem of user communities evolution in  ... 
doi:10.1007/s11280-015-0356-y fatcat:uulmqqc4sneh3mlaqw3zlrpmly

Meta-Path-based Fake News Detection Leveraging Multi-level Social Context Information [article]

Jian Cui, Kwanwoo Kim, Seung Ho Na, Seungwon Shin
2021 arXiv   pre-print
Meta-Path, a composite relation connecting two node types, is proposed to capture the semantics in the heterogeneous graph.  ...  The multi-level social context information (news publishers and engaged users in social media) and temporal information of user engagement are important information in fake news detection.  ...  Users' profiles are used for user nodes since the importance of the user profiles for detecting news authenticity has been proved by Shu, Kai et al. [43] .  ... 
arXiv:2109.08022v2 fatcat:5xjcwantkfgcplvn5pkb642mqe

BotRGCN: Twitter Bot Detection with Relational Graph Convolutional Networks [article]

Shangbin Feng, Herun Wan, Ningnan Wang, Minnan Luo
2021 arXiv   pre-print
BotRGCN addresses the challenge of community by constructing a heterogeneous graph from follow relationships and apply relational graph convolutional networks to the Twittersphere.  ...  To address these two challenges of Twitter bot detection, we propose BotRGCN, which is short for Bot detection with Relational Graph Convolutional Networks.  ...  By defining two sets of relational neighborhood for each Twitter user, BotRGCN constructs a heterogeneous graph that reflects the interactions between Twitter users. BotRGCN architecture.  ... 
arXiv:2106.13092v3 fatcat:lidg3uqt55ctvkqvoagszvltgq
« Previous Showing results 1 — 15 out of 26,214 results