6,656 Hits in 7.6 sec

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
To address this problem, recent research developments can fall into three major lines: social recommendation, knowledge graph-enhanced recommender system, and multi-behavior recommendation.  ...  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  ...  ., 2019c] devises a dual-stage graph attention to dynamic weigh social effects from user and item domain context.  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation [article]

Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Xiyue Zhang, Hongsheng Yang, Jian Pei, Liefeng Bo
2021 arXiv   pre-print
Specifically, KHGT is built upon a graph-structured neural architecture to i) capture type-specific behavior characteristics; ii) explicitly discriminate which types of user-item interactions are more  ...  important in assisting the forecasting task on the target behavior.  ...  Additionally, how to account for the side knowledge from items as well as user-item interaction dynamics, is less explored in those multi-behavior recommender systems.  ... 
arXiv:2110.04000v1 fatcat:44xhyegydzbmzlf5ytlznzhrqm

Data-driven Computational Social Science: A Survey

Jun Zhang, Wei Wang, Feng Xia, Yu-Ru Lin, Hanghang Tong
2020 Big Data Research  
With the aids of the advanced research techniques, various kinds of data from diverse areas can be acquired nowadays, and they can help us look into social problems with a new eye.  ...  The state-of-the-art research on human dynamics is reviewed from three aspects: individuals, relationships, and collectives.  ...  [94] proposed a new social interaction-based approach to identify Facebook community, where social interaction refers to users interacting behaviors with others, such as posting, reading, replying,  ... 
doi:10.1016/j.bdr.2020.100145 fatcat:jazh5b3itfgmvh4pn37l4v5m7y

How events unfold

Ting Hua, Liang Zhao, Feng Chen, Chang-Tien Lu, Naren Ramakrishnan
2016 SIGSPATIAL Special  
event forecasting.  ...  There has been significant recent interest in the application of social media analytics for spatiotemporal event mining. However, no structured survey exists to capture developments in this space.  ...  It is also possible to capture diversity in information flows: for instance, a user can obtain information from a friend's tweets in his/her social network or obtain the necessary information externally  ... 
doi:10.1145/2876480.2876485 fatcat:34dx66my65b4pobofkioeaqknm

Data science and AI in FinTech: An overview [article]

Longbing Cao, Qiang Yang, Philip S. Yu
2021 arXiv   pre-print
, recognition and responses, data analytics, deep learning, federated learning, privacy-preserving processing, augmentation, optimization, and system intelligence enhancement.  ...  of smart FinTech futures to the DSAI communities.  ...  -Behavior and event analysis: including user modeling of online and social behaviors and people's lifestyle; extraction and classification of financial events from news articles; trajectory prediction  ... 
arXiv:2007.12681v2 fatcat:jntzuwaktjg2hmmjypi5lvyht4

Knowledge-aware Coupled Graph Neural Network for Social Recommendation [article]

Chao Huang, Huance Xu, Yong Xu, Peng Dai, Lianghao Xia, Mengyin Lu, Liefeng Bo, Hao Xing, Xiaoping Lai, Yanfang Ye
2021 arXiv   pre-print
capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques.  ...  Social recommendation task aims to predict users' preferences over items with the incorporation of social connections among users, so as to alleviate the sparse issue of collaborative filtering.  ...  Third, the time dimension of the social recommendation deserves more investigation, so as to capture behavior dynamics.  ... 
arXiv:2110.03987v1 fatcat:ra6xspadufe5dfjgntb5mfxlli

Graph Neural Networks in IoT: A Survey [article]

Guimin Dong, Mingyue Tang, Zhiyuan Wang, Jiechao Gao, Sikun Guo, Lihua Cai, Robert Gutierrez, Bradford Campbell, Laura E. Barnes, Mehdi Boukhechba
2022 arXiv   pre-print
Graph Neural Networks (GNNs), an emerging and fast-growing family of neural network models, can capture complex interactions within sensor topology and have been demonstrated to achieve state-of-the-art  ...  Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data.  ...  Dong et al. linked sequential human states (mobility behavior, physical activity, social interaction) to construct graphs.  ... 
arXiv:2203.15935v2 fatcat:jkqg5ukg5fezbewu5mr5hqsp4e

Conditional Generative Adversarial Networks for Speed Control in Trajectory Simulation [article]

Sahib Julka, Vishal Sowrirajan, Joerg Schloetterer, Michael Granitzer
2021 arXiv   pre-print
Further, most endeavours invest heavily in designing special mechanisms to learn the interactions in latent space.  ...  We present Conditional Speed GAN (CSG), that allows controlled generation of diverse and socially acceptable trajectories, based on user controlled speed.  ...  Introduction Modelling social interactions and the ability to forecast motion dynamics is pertinent to several application domains such as robot planning systems [1] , traffic operations [2] , and autonomous  ... 
arXiv:2103.11471v1 fatcat:o2o5uddd4ndwjazdqva2ykvusa

Analysis of various Characteristics of Online User Behavior Models

Dhanashree Deshpande, Shrinivas Deshpande
2017 International Journal of Computer Applications  
Few metrics are used to deviate malicious users from good one. Security is the main concern need to provide to various online applications.  ...  Keywords k-means, Markov Logic Network, online user behavior, social network, user behavior model  ...  The characteristics of Intrusion detection system (IDS) is studied which was used to classify user behavior.  ... 
doi:10.5120/ijca2017913127 fatcat:wkjlosfax5gwve3iq46fsdbkw4

2019 Index IEEE Transactions on Knowledge and Data Engineering Vol. 31

2020 IEEE Transactions on Knowledge and Data Engineering  
., +, TKDE Feb. 2019 385-400 User Preference Analysis for Most Frequent Peer/Dominator. Deng, K., +, Learning Customer Behaviors for Effective Load Forecasting.  ...  ., +, TKDE May 2019 923-937 Learning Customer Behaviors for Effective Load Forecasting. Wang, X., +, TKDE May 2019 938-951 Location Inference for Non-Geotagged Tweets in User Timelines.  ... 
doi:10.1109/tkde.2019.2953412 fatcat:jkmpnsjcf5a3bhhf4ian66mj5y

Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network

Lianghao Xia, Chao Huang, Yong Xu, Peng Dai, Bo Zhang, Liefeng Bo
2020 Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval  
In our MATN framework, we first develop a transformer-based multi-behavior relation encoder, to make the learned interaction representations be reflective of the cross-type behavior relations.  ...  However, user-item interactive behavior is often exhibited with multi-type (e.g., page view, add-to-favorite and purchase) and inter-dependent in nature.  ...  To capture the rich graph-based neighborhood contextual signals, various graph neural encoders have been proposed to aggregate information over the user-item interaction graph, with the graph convolutional  ... 
doi:10.1145/3397271.3401445 dblp:conf/sigir/XiaHXDZB20 fatcat:vn6dqjgycfhtfixke6g4m554ie

Bitcoin Transaction Forecasting with Deep Network Representation Learning [article]

Wenqi Wei, Qi Zhang, Ling Liu
2022 arXiv   pre-print
performance by 50\% when compared to forecasting model built on the static graph baseline.  ...  To maintain an effective transaction forecasting performance, we leverage the multiplicative model update (MMU) ensemble to combine prediction models built on different transaction features extracted from  ...  While these features are not unique for the Bitcoin transaction data but to all dynamic graphs, they reveal the transaction behavior of Bitcoin users.  ... 
arXiv:2007.07993v2 fatcat:mmv65lfztre55m7budnj3y2juy

Predicting Vehicles Trajectories in Urban Scenarios with Transformer Networks and Augmented Information [article]

A. Quintanar, D. Fernández-Llorca, I. Parra, R. Izquierdo, M. A. Sotelo
2021 arXiv   pre-print
Understanding the behavior of road users is of vital importance for the development of trajectory prediction systems.  ...  In this context, the latest advances have focused on recurrent structures, establishing the social interaction between the agents involved in the scene.  ...  Another interesting approach to model spatial interactions for trajectory forecast is through Graph Convolutional (GNN) or Graph Attention (GAT) Networks.  ... 
arXiv:2106.00559v2 fatcat:qofkflvrtnhgzigs2xcrqkmxiu

Enhanced Scalable Learning for Identifying and Ranking for Big Data Using Social Media Factors

Preethi L., Periyasamy Dr.S.
2018 Bonfring International Journal of Software Engineering and Soft Computing  
In recent period, social media services provide a vast amount of user-generated data, which have great potential to contain informative newsrelated content.  ...  The cases are encoded in terms of features in some numerical form, requiring a transformation from text to numbers and assign the positive and negative values to each word to classify the word in the document  ...  Our framework matches the interacting user to the users of social media platforms exhibiting similar taste.  ... 
doi:10.9756/bijsesc.8386 fatcat:eqhpnhud2bccflbs246kq6w3iy

DROGON: A Trajectory Prediction Model based on Intention-Conditioned Behavior Reasoning [article]

Chiho Choi, Srikanth Malla, Abhishek Patil, Joon Hee Choi
2020 arXiv   pre-print
To succeed in such behavior reasoning, we build a conditional prediction model to forecast goal-oriented trajectories with the following stages: (i) relational inference where we encode relational interactions  ...  Our main insight is that the behavior (i.e., motion) of drivers can be reasoned from their high level possible goals (i.e., intention) on the road.  ...  Preliminaries Spatio-Temporal Interactions Spatio-temporal interactions between road users have been considered as one of the most important features to understand their social behaviors.  ... 
arXiv:1908.00024v3 fatcat:whzxjxgyyfbwrf3otafoopdqgy
« Previous Showing results 1 — 15 out of 6,656 results