scholarly journals TensorCast: Forecasting Time-Evolving Networks with Contextual Information

2018 ◽  
Author(s):  
Miguel Araújo ◽  
Pedro Ribeiro ◽  
Christos Faloutsos
Keyword(s):  
Social Network ◽  
Real World ◽  
Large Scale ◽  
Information Sources ◽  
Contextual Information ◽  
Temporal Networks ◽  
Evolving Networks ◽  
Award Winning ◽  
Data Source

Can we forecast future connections in a social network? Can we predict who will start using a given hashtag in Twitter, leveraging contextual information such as who follows or retweets whom to improve our predictions? In this paper we present an abridged report of TensorCast, an award winning method for forecasting time-evolving networks, that uses coupled tensors to incorporate multiple information sources. TensorCast is scalable (linearithmic on the number of connections), effective (more precise than competing methods) and general (applicable to any data source representable by a tensor). We also showcase our method when applied to forecast two large scale heterogeneous real world temporal networks, namely Twitter and DBLP.

scholarly journals Attention Enhanced Serial Unet++ Network for Removing Unevenly Distributed Haze

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2868
Author(s):  
Wenxuan Zhao ◽  
Yaqin Zhao ◽  
Liqi Feng ◽  
Jiaxi Tang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real World ◽  
Large Scale ◽  
Learning Strategy ◽  
Contextual Information ◽  
Small Scale ◽  
Image Dehazing ◽  
Atmospheric Scattering ◽  
Real World Datasets

The purpose of image dehazing is the reduction of the image degradation caused by suspended particles for supporting high-level visual tasks. Besides the atmospheric scattering model, convolutional neural network (CNN) has been used for image dehazing. However, the existing image dehazing algorithms are limited in face of unevenly distributed haze and dense haze in real-world scenes. In this paper, we propose a novel end-to-end convolutional neural network called attention enhanced serial Unet++ dehazing network (AESUnet) for single image dehazing. We attempt to build a serial Unet++ structure that adopts a serial strategy of two pruned Unet++ blocks based on residual connection. Compared with the simple Encoder–Decoder structure, the serial Unet++ module can better use the features extracted by encoders and promote contextual information fusion in different resolutions. In addition, we take some improvement measures to the Unet++ module, such as pruning, introducing the convolutional module with ResNet structure, and a residual learning strategy. Thus, the serial Unet++ module can generate more realistic images with less color distortion. Furthermore, following the serial Unet++ blocks, an attention mechanism is introduced to pay different attention to haze regions with different concentrations by learning weights in the spatial domain and channel domain. Experiments are conducted on two representative datasets: the large-scale synthetic dataset RESIDE and the small-scale real-world datasets I-HAZY and O-HAZY. The experimental results show that the proposed dehazing network is not only comparable to state-of-the-art methods for the RESIDE synthetic datasets, but also surpasses them by a very large margin for the I-HAZY and O-HAZY real-world dataset.

scholarly journals Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation

2020 ◽  
Author(s):  
Ruobing Xie ◽  
Zhijie Qiu ◽  
Jun Rao ◽  
Yi Liu ◽  
Bo Zhang ◽  
...  
Keyword(s):  
Real World ◽  
Large Scale ◽  
Recommendation System ◽  
Contextual Information ◽  
Recommendation Systems ◽  
Cold Start ◽  
Personalized Recommendation ◽  
Small Subset ◽  
Multiple Channels ◽  
Attention Network

Real-world integrated personalized recommendation systems usually deal with millions of heterogeneous items. It is extremely challenging to conduct full corpus retrieval with complicated models due to the tremendous computation costs. Hence, most large-scale recommendation systems consist of two modules: a multi-channel matching module to efficiently retrieve a small subset of candidates, and a ranking module for precise personalized recommendation. However, multi-channel matching usually suffers from cold-start problems when adding new channels or new data sources. To solve this issue, we propose a novel Internal and contextual attention network (ICAN), which highlights channel-specific contextual information and feature field interactions between multiple channels. In experiments, we conduct both offline and online evaluations with case studies on a real-world integrated recommendation system. The significant improvements confirm the effectiveness and robustness of ICAN, especially for cold-start channels. Currently, ICAN has been deployed on WeChat Top Stories used by millions of users. The source code can be obtained from https://github.com/zhijieqiu/ICAN.

scholarly journals The Finding and Dynamic Detection of Opinion Leaders in Social Network

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Baocheng Huang ◽  
Guang Yu ◽  
Hamid Reza Karimi
Keyword(s):  
Social Network ◽  
Real World ◽  
Structural Characteristics ◽  
Detection Algorithm ◽  
Experimental Results ◽  
Opinion Leaders ◽  
Data Sources ◽  
The Real ◽  
Data Source ◽  
Different Characteristics

It is valuable for the real world to find the opinion leaders. Because different data sources usually have different characteristics, there does not exist a standard algorithm to find and detect the opinion leaders in different data sources. Every data source has its own structural characteristics, and also has its own detection algorithm to find the opinion leaders. Experimental results show the opinion leaders and theirs characteristics can be found among the comments from the Weibo social network of China, which is like Facebook or Twitter in USA.

scholarly journals Generating a heterosexual bipartite network embedded in social network

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Asma Azizi ◽  
Zhuolin Qu ◽  
Bryan Lewis ◽  
James Mac Hyman
Keyword(s):  
Social Network ◽  
Real World ◽  
Large Scale ◽  
Social Contact ◽  
Contact Network ◽  
Bipartite Network ◽  
Sexual Networks ◽  
Sexual Network ◽  
Activity Data ◽  
The Social

AbstractWe describe an approach to generate a heterosexual network with a prescribed joint-degree distribution embedded in a prescribed large-scale social contact network. The structure of a sexual network plays an important role in how all sexually transmitted infections (STIs) spread. Generating an ensemble of networks that mimics the real-world is crucial to evaluating robust mitigation strategies for controlling STIs. Most of the current algorithms to generate sexual networks only use sexual activity data, such as the number of partners per month, to generate the sexual network. Real-world sexual networks also depend on biased mixing based on age, location, and social and work activities. We describe an approach to use a broad range of social activity data to generate possible heterosexual networks. We start with a large-scale simulation of thousands of people in a city as they go through their daily activities, including work, school, shopping, and activities at home. We extract a social network from these activities where the nodes are the people, and the edges indicate a social interaction, such as working in the same location. This social network captures the correlations between people of different ages, living in different locations, their economic status, and other demographic factors. We use the social contact network to define a bipartite heterosexual network that is embedded within an extended social network. The resulting sexual network captures the biased mixing inherent in the social network, and models based on this pairing of networks can be used to investigate novel intervention strategies based on the social contacts among infected people. We illustrate the approach in a model for the spread of chlamydia in the heterosexual network representing the young sexually active community in New Orleans.

scholarly journals GAEN: Graph Attention Evolving Networks

2021 ◽  
Author(s):  
Min Shi ◽  
Yu Huang ◽  
Xingquan Zhu ◽  
Yufei Tang ◽  
Yuan Zhuang ◽  
...  
Keyword(s):  
Temporal Variation ◽  
Real World ◽  
Dynamic Properties ◽  
Dynamic Networks ◽  
Dynamic Network ◽  
Representation Learning ◽  
Temporal Networks ◽  
Network Nodes ◽  
Evolving Networks ◽  
Variation Patterns

Real-world networked systems often show dynamic properties with continuously evolving network nodes and topology over time. When learning from dynamic networks, it is beneficial to correlate all temporal networks to fully capture the similarity/relevance between nodes. Recent work for dynamic network representation learning typically trains each single network independently and imposes relevance regularization on the network learning at different time steps. Such a snapshot scheme fails to leverage topology similarity between temporal networks for progressive training. In addition to the static node relationships within each network, nodes could show similar variation patterns (e.g., change of local structures) within the temporal network sequence. Both static node structures and temporal variation patterns can be combined to better characterize node affinities for unified embedding learning. In this paper, we propose Graph Attention Evolving Networks (GAEN) for dynamic network embedding with preserved similarities between nodes derived from their temporal variation patterns. Instead of training graph attention weights for each network independently, we allow model weights to share and evolve across all temporal networks based on their respective topology discrepancies. Experiments and validations, on four real-world dynamic graphs, demonstrate that GAEN outperforms the state-of-the-art in both link prediction and node classification tasks.

scholarly journals Supervised temporal link prediction in large-scale real-world networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Gerrit Jan de Bruin ◽  
Cor J. Veenman ◽  
H. Jaap van den Herik ◽  
Frank W. Takes
Keyword(s):  
Real World ◽  
Link Prediction ◽  
Large Scale ◽  
Systematic Investigation ◽  
Prediction Performance ◽  
Temporal Information ◽  
Temporal Networks ◽  
Discrete Events ◽  
New Approach ◽  
Topological Features

AbstractLink prediction is a well-studied technique for inferring the missing edges between two nodes in some static representation of a network. In modern day social networks, the timestamps associated with each link can be used to predict future links between so-far unconnected nodes. In these so-called temporal networks, we speak of temporal link prediction. This paper presents a systematic investigation of supervised temporal link prediction on 26 temporal, structurally diverse, real-world networks ranging from thousands to a million nodes and links. We analyse the relation between global structural properties of each network and the obtained temporal link prediction performance, employing a set of well-established topological features commonly used in the link prediction literature. We report on four contributions. First, using temporal information, an improvement of prediction performance is observed. Second, our experiments show that degree disassortative networks perform better in temporal link prediction than assortative networks. Third, we present a new approach to investigate the distinction between networks modelling discrete events and networks modelling persistent relations. Unlike earlier work, our approach utilises information on all past events in a systematic way, resulting in substantially higher link prediction performance. Fourth, we report on the influence of the temporal activity of the node or the edge on the link prediction performance, and show that the performance differs depending on the considered network type. In the studied information networks, temporal information on the node appears most important. The findings in this paper demonstrate how link prediction can effectively be improved in temporal networks, explicitly taking into account the type of connectivity modelled by the temporal edge. More generally, the findings contribute to a better understanding of the mechanisms behind the evolution of networks.

1588-P: Therapy Trends in Initial 6 Months of the First Large-Scale Longitudinal Nationwide Study on Management and Real-World Outcomes of Diabetes in India (LANDMARC)

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 1588-P ◽  
Author(s):  
ROMIK GHOSH ◽  
ASHOK K. DAS ◽  
AMBRISH MITHAL ◽  
SHASHANK JOSHI ◽  
K.M. PRASANNA KUMAR ◽  
...  
Keyword(s):  
Real World ◽  
Large Scale ◽  
Nationwide Study

2258-PUB: Impact of Cardiovascular (CV) Risk Factors during the Initial 6 Months of the First Large-Scale Longitudinal Nationwide Study on Management and Real-World Outcomes of Diabetes in India (LANDMARC)

Diabetes ◽  
2020 ◽  
Vol 69 (Supplement 1) ◽  
pp. 2258-PUB
Author(s):  
ROMIK GHOSH ◽  
ASHOK K. DAS ◽  
SHASHANK JOSHI ◽  
AMBRISH MITHAL ◽  
K.M. PRASANNA KUMAR ◽  
...  
Keyword(s):  
Risk Factors ◽  
Real World ◽  
Large Scale ◽  
Nationwide Study

Mapping the Topics and Evolutions of Chinese Children’s Bestsellers

Libri ◽  
2020 ◽  
Vol 70 (4) ◽  
pp. 305-317
Author(s):  
Jiming Hu ◽  
Xiang Zheng ◽  
Peng Wen ◽  
Jie Xu
Keyword(s):  
Social Network ◽  
Quantitative Analysis ◽  
Network Analysis ◽  
Intellectual Structure ◽  
Structure Evolution ◽  
Children's Books ◽  
Children’S Books ◽  
Correlation Structures ◽  
The World ◽  
Data Source

AbstractChildren’s books involve a large number of topics. Research on them has been paid much attention to by both scholars and practitioners. However, the existing achievements do not focus on China, which is the fastest growing market for children’s books in the world. Studies using quantitative analysis are low in number, especially on the intellectual structure, evolution patterns, and development trends of topics of children’s bestsellers in China. Dangdang.com, the biggest Chinese online bookstore, was chosen as a data source to obtain children’s bestsellers, and topic words in them were extracted from brief introductions. With the aid of co-occurrence theory and tools of social network analysis and visualization, the distribution, correlation structures, and evolution patterns of topics were revealed and visualized. This study shows that topics of Chinese children’s bestsellers are broad and relatively concentrated, but their distribution is unbalanced. There are four distinguished topic communities (Living, Animal, World, and Child) in terms of centrality and maturity, and they all establish their individual systems and tend to be mature. The evolution of these communities tends to be stable with powerful continuity.

Sign in / Sign up

Export Citation Format

Share Document