scholarly journals Network Embedding under Partial Monitoring for Evolving Networks

2019 ◽  
Author(s):  
Yu Han ◽  
Jie Tang ◽  
Qian Chen
Keyword(s):  
Real World ◽  
Dynamic Networks ◽  
Dynamic Network ◽  
Actual Situation ◽  
Challenging Problem ◽  
Network Embedding ◽  
Strong Assumption ◽  
Evolving Networks ◽  
Real World Datasets ◽  
The Web

Network embedding has been extensively studied in recent years. In addition to the works on static networks, some researchers try to propose new models for evolving networks. However, sometimes most of these dynamic network embedding models are still not in line with the actual situation, since these models have a strong assumption that we can achieve all the changes in the whole network, while in fact we cannot do this in some real world networks, such as the web networks and some large social networks. So in this paper, we study a novel and challenging problem, i.e., network embedding under partial monitoring for evolving networks. We propose a model on dynamic networks in which we cannot perceive all the changes of the structure. We analyze our model theoretically, and give a bound to the error between the results of our model and the potential optimal cases. We evaluate the performance of our model from two aspects. The experimental results on real world datasets show that our model outperforms the baseline models by a large margin.

scholarly journals Towards Robust Dynamic Network Embedding

2021 ◽  
Author(s):  
Chengbin Hou ◽  
Ke Tang
Keyword(s):  
Real World ◽  
Dynamic Networks ◽  
Dynamic Network ◽  
Network Embedding ◽  
Dynamic Nature ◽  
Unique Character

Dynamic Network Embedding (DNE) has recently drawn much attention due to the dynamic nature of many real-world networks. Comparing to a static network, a dynamic network has a unique character called the degree of changes, which can be defined as the average number of the changed edges between consecutive snapshots spanning a dynamic network. The degree of changes could be quite different even for the dynamic networks generated from the same dataset. It is natural to ask whether existing DNE methods are effective and robust w.r.t. the degree of changes. Towards robust DNE, we suggest two important scenarios. One is to investigate the robustness w.r.t. different slicing settings that are used to generate different dynamic networks with different degree of changes, while another focuses more on the robustness w.r.t. different number of changed edges over timesteps.

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 Relation Structure-Aware Heterogeneous Information Network Embedding

2019 ◽  
Vol 33 ◽  
pp. 4456-4463 ◽  
Author(s):  
Yuanfu Lu ◽  
Chuan Shi ◽  
Linmei Hu ◽  
Zhiyuan Liu
Keyword(s):  
Real World ◽  
Dimensional Space ◽  
Structural Characteristics ◽  
Information Network ◽  
Network Embedding ◽  
Heterogeneous Information Network ◽  
Heterogeneous Information ◽  
Real World Datasets ◽  
Low Dimensional ◽  
Embedding Methods

Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.

Identifying influential nodes in dynamic social networks based on degree-corrected stochastic block model

2016 ◽  
Vol 30 (16) ◽  
pp. 1650092 ◽  
Author(s):  
Tingting Wang ◽  
Weidi Dai ◽  
Pengfei Jiao ◽  
Wenjun Wang
Keyword(s):  
Social Networks ◽  
Real World ◽  
Dynamic Networks ◽  
Dynamic Network ◽  
Community Structures ◽  
Block Model ◽  
Real World Data ◽  
Stochastic Block Model ◽  
Dynamic Social Networks ◽  
Influential Nodes

Many real-world data can be represented as dynamic networks which are the evolutionary networks with timestamps. Analyzing dynamic attributes is important to understanding the structures and functions of these complex networks. Especially, studying the influential nodes is significant to exploring and analyzing networks. In this paper, we propose a method to identify influential nodes in dynamic social networks based on identifying such nodes in the temporal communities which make up the dynamic networks. Firstly, we detect the community structures of all the snapshot networks based on the degree-corrected stochastic block model (DCBM). After getting the community structures, we capture the evolution of every community in the dynamic network by the extended Jaccard’s coefficient which is defined to map communities among all the snapshot networks. Then we obtain the initial influential nodes of the dynamic network and aggregate them based on three widely used centrality metrics. Experiments on real-world and synthetic datasets demonstrate that our method can identify influential nodes in dynamic networks accurately, at the same time, we also find some interesting phenomena and conclusions for those that have been validated in complex network or social science.

IncNSA: Detecting communities incrementally from time-evolving networks based on node similarity

2020 ◽  
Vol 31 (07) ◽  
pp. 2050094
Author(s):  
Xing Su ◽  
Jianjun Cheng ◽  
Haijuan Yang ◽  
Mingwei Leng ◽  
Wenbo Zhang ◽  
...  
Keyword(s):  
Real World ◽  
Detection Method ◽  
Dynamic Networks ◽  
Second Phase ◽  
World Systems ◽  
Evolving Networks ◽  
The Third ◽  
Third Phase ◽  
Node Similarity ◽  
Over Time

Many real-world systems can be abstracted as networks. As those systems always change dynamically in nature, the corresponding networks also evolve over time in general, and detecting communities from such time-evolving networks has become a critical task. In this paper, we propose an incremental detection method, which can stably detect high-quality community structures from time-evolving networks. When the network evolves from the previous snapshot to the current one, the proposed method only considers the community affiliations of partial nodes efficiently, which are either newborn nodes or some active nodes from the previous snapshot. Thus, the first phase of our method is determining active nodes that should be reassigned due to the change of their community affiliations in the evolution. Then, we construct subgraphs for these nodes to obtain the preliminary communities in the second phase. Finally, the final result can be obtained through optimizing the primary communities in the third phase. To test its performance, extensive experiments are conducted on both some synthetic networks and some real-world dynamic networks, the results show that our method can detect satisfactory community structure from each of snapshot graphs efficiently and steadily, and outperforms the competitors significantly.

scholarly journals From the Periphery to the Core: Information Brokerage in an Evolving Network

2018 ◽  
Author(s):  
Bo Yan ◽  
Yiping Liu ◽  
Jiamou Liu ◽  
Yijin Cai ◽  
Hongyi Su ◽  
...  
Keyword(s):  
Network Dynamics ◽  
Dynamic Networks ◽  
Dynamic Network ◽  
Network Models ◽  
Relationship Building ◽  
Superior Performance ◽  
Alternative Methods ◽  
Real World Datasets ◽  
And Performance ◽  
Interpersonal Ties

Interpersonal ties are pivotal to individual efficacy, status and performance in an agent society.This paper explores three important and interrelated themes in social network theory: the center/periphery partition of the network; network dynamics; and social integration of newcomers. We tackle the question: How would a newcomer harness information brokerage to integrate into a dynamic network going from periphery to center? We model integration as the interplay between the newcomer and the dynamics network and capture information brokerage using a process of relationship building. We analyze theoretical guarantees for the newcomer to reach the center through tactics; proving that a winning tactic always exists for certain types of network dynamics. We then propose three tactics and show their superior performance over alternative methods on four real-world datasets and four network models. In general, our tactics place the newcomer to the center by adding very few new edges on dynamic networks with ~14000 nodes.

scholarly journals Analysis of Regular Patterns in Un-weighted Directed Graphs

2022 ◽  
Vol 12 (1) ◽  
pp. 0-0
Keyword(s):  
Real World ◽  
Directed Graphs ◽  
Degree Centrality ◽  
Relative Significance ◽  
Evolving Networks ◽  
Graph Metrics ◽  
Mining Algorithm ◽  
Real World Datasets ◽  
Regular Patterns

Time evolving networks tend to have an element of regularity. This regularity is characterized by existence of repetitive patterns in the data sequences of the graph metrics. As per our research, the relevance of such regular patterns to the network has not been adequately explored. Such patterns in certain data sequences are indicative of properties like popularity, activeness etc. which are of vital significance for any network. These properties are closely indicated by data sequences of graph metrics - degree prestige, degree centrality and occurrence. In this paper, (a) an improved mining algorithm has been used to extract regular patterns in these sequences, and (b) a methodology has been proposed to quantitatively analyse the behavior of the obtained patterns. To analyze this behavior, a quantification measure coined as "Sumscore" has been defined to compare the relative significance of such patterns. The patterns are ranked according to their Sumscores and insights are then drawn upon it. The efficacy of this method is demonstrated by experiments on two real world datasets.

scholarly journals Discrete Embedding for Latent Networks

2020 ◽  
Author(s):  
Hong Yang ◽  
Ling Chen ◽  
Minglong Lei ◽  
Lingfeng Niu ◽  
Chuan Zhou ◽  
...  
Keyword(s):  
Real World ◽  
Representation Learning ◽  
Mixed Integer ◽  
Information Cascades ◽  
Integer Optimization ◽  
Network Embedding ◽  
Structure Information ◽  
Proximity Matrix ◽  
Real World Datasets ◽  
Embedding Methods

Discrete network embedding emerged recently as a new direction of network representation learning. Compared with traditional network embedding models, discrete network embedding aims to compress model size and accelerate model inference by learning a set of short binary codes for network vertices. However, existing discrete network embedding methods usually assume that the network structures (e.g., edge weights) are readily available. In real-world scenarios such as social networks, sometimes it is impossible to collect explicit network structure information and it usually needs to be inferred from implicit data such as information cascades in the networks. To address this issue, we present an end-to-end discrete network embedding model for latent networks DELN that can learn binary representations from underlying information cascades. The essential idea is to infer a latent Weisfeiler-Lehman proximity matrix that captures node dependence based on information cascades and then to factorize the latent Weisfiler-Lehman matrix under the binary node representation constraint. Since the learning problem is a mixed integer optimization problem, an efficient maximal likelihood estimation based cyclic coordinate descent (MLE-CCD) algorithm is used as the solution. Experiments on real-world datasets show that the proposed model outperforms the state-of-the-art network embedding methods.

scholarly journals Inferring Substitutable Products with Deep Network Embedding

2019 ◽  
Author(s):  
Shijie Zhang ◽  
Hongzhi Yin ◽  
Qinyong Wang ◽  
Tong Chen ◽  
Hongxu Chen ◽  
...  
Keyword(s):  
Semantic Similarity ◽  
Real World ◽  
State Of The Art ◽  
Network Embedding ◽  
Online Transactions ◽  
First Order ◽  
Substitutable Products ◽  
Deep Embedding ◽  
Real World Datasets ◽  
Explicit Feedback

On E-commerce platforms, understanding the relationships (e.g., substitute and complement) among products from user's explicit feedback, such as users' online transactions, is of great importance to boost extra sales. However, the significance of such relationships is usually neglected by existing recommender systems. In this paper, we propose a semisupervised deep embedding model, namely, Substitute Products Embedding Model (SPEM), which models the substitutable relationships between products by preserving the second-order proximity, negative first-order proximity and semantic similarity in a product co-purchasing graph based on user's purchasing behaviours. With SPEM, the learned representations of two substitutable products align closely in the latent embedding space. Extensive experiments on real-world datasets are conducted, and the results verify that our model outperforms state-of-the-art baselines.

scholarly journals Learning Sequential Correlation for User Generated Textual Content Popularity Prediction

2018 ◽  
Author(s):  
Wen Wang ◽  
Wei Zhang ◽  
Jun Wang ◽  
Junchi Yan ◽  
Hongyuan Zha
Keyword(s):  
Real World ◽  
Information Overload ◽  
Representation Learning ◽  
Text Representation ◽  
Sequential Model ◽  
Content Popularity ◽  
Popularity Prediction ◽  
Real World Datasets ◽  
Textual Content ◽  
The Web

Popularity prediction of user generated textual content is critical for prioritizing information in the web, which alleviates heavy information overload for ordinary readers. Most previous studies model each content instance separately for prediction and thus overlook the sequential correlations between instances of a specific user. In this paper, we go deeper into this problem based on the two observations for each user, i.e., sequential content correlation and sequential popularity correlation. We propose a novel deep sequential model called User Memory-augmented recurrent Attention Network (UMAN). This model encodes the two correlations by updating external user memories which is further leveraged for target text representation learning and popularity prediction. The experimental results on several real-world datasets validate the benefits of considering these correlations and demonstrate UMAN achieves best performance among several strong competitors.

Sign in / Sign up

Export Citation Format

Share Document