7,420 Hits in 4.2 sec

Towards Job-Transition-Tag Graph for a Better Job Title Representation Learning [article]

Jun Zhu, Céline Hudelot
2022 arXiv   pre-print
Specifically, we construct Job-Transition-Tag Graph, a heterogeneous graph containing two types of nodes, i.e., job titles and tags (i.e., words related to job responsibilities or functionalities).  ...  Along this line, we reformulate job title representation learning as the task of learning node embedding on the Job-Transition-Tag Graph. Experiments on two datasets show the interest of our approach.  ...  We would like to thank the Mésocentre 5 computing center of Cen-traleSupélec and École Normale Supérieure Paris-Saclay for providing computing resources.  ... 
arXiv:2206.02782v1 fatcat:qqxg2em3ybgt5berdpbyxqvuny

Dual-Level Attention Based on a Heterogeneous Graph Convolution Network for Aspect-Based Sentiment Classification

Peng Yuan, Lei Jiang, Jianxun Liu, Dong Zhou, Pei Li, Yang Gao, Yan Huang
2021 Wireless Communications and Mobile Computing  
To address these issues, we propose a novel dual-level attention-based heterogeneous graph convolutional network for aspect-based sentiment classification which minds more context information through information  ...  Then, we propose a dual-level attention-based heterogeneous graph convolutional network (DAHGCN), which includes node-level and type-level attentions.  ...  Then, we propose a dual-level attention based on a heterogeneous graph convolutional network for aspect-based sentiment analysis.  ... 
doi:10.1155/2021/6625899 fatcat:w5imgeshljblvkanuazdm3hqhi

Spatial-Temporal Meta-path Guided Explainable Crime Prediction [article]

Yuting Sun and Tong Chen and Hongzhi Yin
2022 arXiv   pre-print
., learned embeddings of districts), making it still a challenge to investigate the impacts of explicit factors for the occurrences of crimes behind the scenes.  ...  With the increasing availability of both fine-grained urban and public service data, there is a recent surge in fusing such cross-domain information to facilitate crime prediction.  ...  Radislav Vaisman (the University of Queensland) for valuable discussions on this research and helpful comments on the manuscript.  ... 
arXiv:2205.01901v1 fatcat:q2uao24gnnfztbwd573lpagz24

Saving energy without defying deadlines on mobile GPU-based heterogeneous systems

Arian Maghazeh, Unmesh D. Bordoloi, Adrian Horga, Petru Eles, Zebo Peng
2014 Proceedings of the 2014 International Conference on Hardware/Software Codesign and System Synthesis - CODES '14  
Moreover, in mobile/embedded systems, energy-efficient computing is a major concern and yet, there has been no systematic study on the energy savings that GPUs may potentially provide.  ...  While the suitability of GPUs for throughput oriented applications is well-accepted, their applicability for real-time applications remains an open issue.  ...  In fact, the arrival of embedded GPUs has given the software industry an opportunity to usher in the era of heterogeneous computation for embedded devices as well [1] .  ... 
doi:10.1145/2656075.2656097 dblp:conf/codes/MaghazehBHEP14 fatcat:ipauu4yflje4ho7pz6fxiai55i

Fake News Quick Detection on Dynamic Heterogeneous Information Networks [article]

Jin Ho Go, Alina Sari, Jiaojiao Jiang, Shuiqiao Yang, Sanjay Jha
2022 arXiv   pre-print
Therefore, in this paper, we propose a novel Dynamic Heterogeneous Graph Neural Network (DHGNN) for fake news quick detection.  ...  Then, we construct the heterogeneous news-author graph to reflect contextual information and relationships.  ...  To handle this issue, we propose a novel dynamic heterogeneous attention network, namely Dynamic Heterogeneous Graph Neural Network (DHGNN).  ... 
arXiv:2205.07039v1 fatcat:pobg6btztrbqfenzokuzvqjypm

Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking [article]

Natalia Vesselinova, Rebecca Steinert, Daniel F. Perez-Ramirez, Magnus Boman
2020 arXiv   pre-print
Relevant developments in machine learning research on graphs is surveyed, for this purpose.  ...  Existing approaches to solving combinatorial optimization problems on graphs suffer from the need to engineer each problem algorithmically, with practical problems recurring in many instances.  ...  per-node embeddings (capture information about a DAG node and its neighbors), per-job embedding (aggregate information across a DAG) and a global embedding (summary of per-job embeddings).  ... 
arXiv:2005.11081v1 fatcat:ajqghcevqvdrvdlcrknxlzlqdi

Hybrid Music Recommendation Algorithm Based on Music Gene and Improved Knowledge Graph

Tingting Zhang, Shengnan Liu, Chin-Ling Chen
2022 Security and Communication Networks  
Combining music as a specific recommendation object, a hybrid recommendation algorithm based on music genes and improved knowledge graph is proposed for the traditional single recommendation algorithm  ...  In addition, deep learning method is applied to extract low-dimensional, abstract deep semantic features of users and items, based on which, score prediction is performed.  ...  graph embedding, items and user representations are learned through a single knowledge graph. (4) RKGE: using heterogeneous information encoded by knowledge graphs, a recursive network structure is used  ... 
doi:10.1155/2022/5889724 fatcat:x6xngsp5grdurpziwg3tqvi72m

An Intelligent Task Scheduling Mechanism for Autonomous Vehicles via Deep Learning

Gomatheeshwari Balasekaran, Selvakumar Jayakumar, Rocío Pérez de Prado
2021 Energies  
With the rapid development of the Internet of Things (IoT) and artificial intelligence, autonomous vehicles have received much attention in recent years.  ...  For each task processing, a supervised resource predictor is invoked for optimal hardware cluster selection.  ...  Liu et al. (2017) developed an autonomous driving system architecture that can run tasks on a heterogeneous Advanced Risc Machine (ARM) mobile system-on-chip [23] .  ... 
doi:10.3390/en14061788 fatcat:q7ksrt7tdbbgfckyklcdrjlq5e

TANGO: Transparent heterogeneous hardware Architecture deployment for eNergy Gain in Operation [article]

Karim Djemame and Django Armstrong and Richard Kavanagh and Jean-Christophe Deprez and Ana Juan Ferrer and David Garcia Perez and Rosa Badia and Raul Sirvent and Jorge Ejarque and Yiannis Georgiou
2016 arXiv   pre-print
The paper is concerned with the issue of how software systems actually use Heterogeneous Parallel Architectures (HPAs), with the goal of optimizing power consumption on these resources.  ...  It argues the need for novel methods and tools to support software developers aiming to optimise power consumption resulting from designing, developing, deploying and running software on HPAs, while maintaining  ...  Acknowledgments This work is partly supported by the European Commission under H2020-ICT-20152 contract 687584 -Transparent heterogeneous hardware Architecture deployment for eNergy Gain in Operation (  ... 
arXiv:1603.01407v1 fatcat:3yjffrybxfbondmjgq5vy5fjd4

Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking

Natalia Vesselinova, Rebecca Steinert, Daniel F. Perez-Ramirez, Magnus Boman
2020 IEEE Access  
Relevant developments in machine learning research on graphs are surveyed for this purpose.  ...  Existing approaches to solving combinatorial optimization problems on graphs suffer from the need to engineer each problem algorithmically, with practical problems recurring in many instances.  ...  Junaid Shuja, who coordinated the review process, and to the anonymous reviewers for their expeditious and helpful review comments received in preparation of the final version of the manuscript.  ... 
doi:10.1109/access.2020.3004964 fatcat:v7i7x6p77zfi7dntipxoiolily

A Comprehensive Survey of Graph-based Deep Learning Approaches for Anomaly Detection in Complex Distributed Systems [article]

Armin Danesh Pazho, Ghazal Alinezhad Noghre, Arnab A Purkayastha, Jagannadh Vempati, Otto Martin, Hamed Tabkhi
2022 arXiv   pre-print
Our main focus is to provide an in-depth look at graphs when applied on heterogeneous computing devices spread across complex distributed systems.  ...  In this survey, we explore the significant potential of graph-based algorithms to identify and mitigate different types of anomalies in complex distributed heterogeneous systems.  ...  After the construction of the graph, Graph Attention-Based Forecasting predicts the behavior of sensors in the future time step.  ... 
arXiv:2206.04149v1 fatcat:pprw7huwqvbadozlzhigftgi7u

Spam Review Detection with Graph Convolutional Networks

Ao Li, Zhou Qin, Runshi Liu, Yiqun Yang, Dong Li
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
In this model, a heterogeneous graph and a homogeneous graph are integrated to capture the local context and global context of a comment.  ...  We propose a large-scale anti-spam method based on graph convolutional networks (GCN) for detecting spam advertisements at Xianyu, named GCN-based Anti-Spam (GAS) model.  ...  ACKNOWLEDGEMENTS We would like to thank Yuhong Li, Jun Zhu, Leishi Xu for their assistance on KNN Graph algorithm, and thanks to Huan Zhao for reviews and discussions.  ... 
doi:10.1145/3357384.3357820 dblp:conf/cikm/LiQLYL19 fatcat:dwsye2ycd5b4zja5pt7aexuk3i

Tensor Embedding: A Supervised Framework for Human Behavioral Data Mining and Prediction [article]

Homa Hosseinmardi and Amir Ghasemian and Shrikanth Narayanan and Kristina Lerman and Emilio Ferrara
2018 arXiv   pre-print
We propose a Supervised Tensor Embedding (STE) algorithm for high dimension multimodal data with join decomposition of input and target variable.  ...  Prediction of different aspects of human behavior from these noisy, incomplete, and heterogeneous bio-behavioral temporal data is a challenging problem, beyond unsupervised discovery of latent structures  ...  function for subsequent prediction tasks.  ... 
arXiv:1808.10867v1 fatcat:d72cn7hxqrc4bbyw4wog7pvp4i

Research directions in session-based and sequential recommendation

Dietmar Jannach, Bamshad Mobasher, Shlomo Berkovsky
2020 User modeling and user-adapted interaction  
The embeddings, in turn, are used in a k-nearest-neighbor recommendation framework to recommend jobs.  ...  The underlying time-evolving heterogeneous graph structure consists of users, news items and categories, sessions and other meta-data.  ...  Bamshad Mobasher is a professor of Computer Science and the director of the Center for Web Intelligence at DePaul University.  ... 
doi:10.1007/s11257-020-09274-4 fatcat:tihp3ud43jfptothm47u5xehua

An End-to-end Model of Predicting Diverse Ranking On Heterogeneous Feeds

Zizhe Gao, Zheng Gao, Heng Huang, Zhuoren Jiang, Yuliang Yan
2018 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval  
However, the diversity of feed types raises a challenge for the CSE to rank heterogeneous feeds.  ...  As an external assistance for online shopping, multimedia content (feed) plays an important role in e-Commerce field.  ...  And we use the user & query embeddings as the input for slot feed type prediction. 3.2.2 Type prediction.  ... 
dblp:conf/sigir/GaoGHJY18 fatcat:hspqwxsmmjdnpoi3x6fa4r4vxa
« Previous Showing results 1 — 15 out of 7,420 results