Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks

2022 ◽  
Vol 40 (3) ◽  
pp. 1-21
Author(s):  
Lili Wang ◽  
Chenghan Huang ◽  
Ying Lu ◽  
Weicheng Ma ◽  
Ruibo Liu ◽  
...  

Complex user behavior, especially in settings such as social media, can be organized as time-evolving networks. Through network embedding, we can extract general-purpose vector representations of these dynamic networks which allow us to analyze them without extensive feature engineering. Prior work has shown how to generate network embeddings while preserving the structural role proximity of nodes. These methods, however, cannot capture the temporal evolution of the structural identity of the nodes in dynamic networks. Other works, on the other hand, have focused on learning microscopic dynamic embeddings. Though these methods can learn node representations over dynamic networks, these representations capture the local context of nodes and do not learn the structural roles of nodes. In this article, we propose a novel method for learning structural node embeddings in discrete-time dynamic networks. Our method, called HR2vec , tracks historical topology information in dynamic networks to learn dynamic structural role embeddings. Through experiments on synthetic and real-world temporal datasets, we show that our method outperforms other well-known methods in tasks where structural equivalence and historical information both play important roles. HR2vec can be used to model dynamic user behavior in any networked setting where users can be represented as nodes. Additionally, we propose a novel method (called network fingerprinting) that uses HR2vec embeddings for modeling whole (or partial) time-evolving networks. We showcase our network fingerprinting method on synthetic and real-world networks. Specifically, we demonstrate how our method can be used for detecting foreign-backed information operations on Twitter.

2021 ◽  
pp. 1-12
Author(s):  
Lauro Reyes-Cocoletzi ◽  
Ivan Olmos-Pineda ◽  
J. Arturo Olvera-Lopez

The cornerstone to achieve the development of autonomous ground driving with the lowest possible risk of collision in real traffic environments is the movement estimation obstacle. Predicting trajectories of multiple obstacles in dynamic traffic scenarios is a major challenge, especially when different types of obstacles such as vehicles and pedestrians are involved. According to the issues mentioned, in this work a novel method based on Bayesian dynamic networks is proposed to infer the paths of interest objects (IO). Environmental information is obtained through stereo video, the direction vectors of multiple obstacles are computed and the trajectories with the highest probability of occurrence and the possibility of collision are highlighted. The proposed approach was evaluated using test environments considering different road layouts and multiple obstacles in real-world traffic scenarios. A comparison of the results obtained against the ground truth of the paths taken by each detected IO is performed. According to experimental results, the proposed method obtains a prediction rate of 75% for the change of direction taking into consideration the risk of collision. The importance of the proposal is that it does not obviate the risk of collision in contrast with related work.


Author(s):  
Yu Han ◽  
Jie Tang ◽  
Qian Chen

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.


2020 ◽  
Vol 31 (07) ◽  
pp. 2050094
Author(s):  
Xing Su ◽  
Jianjun Cheng ◽  
Haijuan Yang ◽  
Mingwei Leng ◽  
Wenbo Zhang ◽  
...  

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.


2021 ◽  
Author(s):  
◽  
Alexandra Lee

Any dataset containing information about relationships between entities can be modelled as a network. This network can be static, where the entities/relationships do not change over time, or dynamic, where the entities/relationships change over time. Network data that changes over time, dynamic network data, is a powerful resource when studying many important phenomena, across wide-ranging fields from travel networks to epidemiology.However, it is very difficult to analyse this data, especially if it covers a long period of time (e.g, one month) with respect to its temporal resolution (e.g. seconds). In this thesis, we address the problem of visualising long in time dynamic networks: networks that may not be particularly large in terms of the number of entities or relationships, but are long in terms of the length of time they cover when compared to their temporal resolution.We first introduce Dynamic Network Plaid, a system for the visualisation and analysis of long in time dynamic networks. We design and build for an 84" touch-screen vertically-mounted display as existing work reports positive results for the use of these in a visualisation context, and that they are useful for collaboration. The Plaid integrates multiple views and we prioritise the visualisation of interaction provenance. In this system we also introduce a novel method of time exploration called ‘interactive timeslicing’. This allows the selection and comparison of points that are far apart in time, a feature not offered by existing visualisation systems. The Plaid is validated through an expert user evaluation with three public health researchers.To confirm observations of the expert user evaluation, we then carry out a formal laboratory study with a large touch-screen display to verify our novel method of time navigation against existing animation and small multiples approaches. From this study, we find that interactive timeslicing outperforms animation and small multiples for complex tasks requiring a compari-son between multiple points that are far apart in time. We also find that small multiples is best suited to comparisons of multiple sequential points in time across a time interval.To generalise the results of this experiment, we later run a second formal laboratory study in the same format as the first, but this time using standard-sized displays with indirect mouse input. The second study reaffirms the results of the first, showing that our novel method of time navigation can facilitate the visual comparison of points that are distant in time in a way that existing approaches, small multiples and animation, cannot. The study demonstrates that our previous results generalise across display size and interaction type (touch vs mouse).In this thesis we introduce novel representations and time interaction techniques to improve the visualisation of long in time dynamic networks, and experimentally show that our novel method of time interaction outperforms other popular methods for some task types.


Author(s):  
Min Shi ◽  
Yu Huang ◽  
Xingquan Zhu ◽  
Yufei Tang ◽  
Yuan Zhuang ◽  
...  

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.


2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Weiwei Gu ◽  
Aditya Tandon ◽  
Yong-Yeol Ahn ◽  
Filippo Radicchi

AbstractNetwork embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension – small enough to be efficient and large enough to be effective – is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Seyed Hossein Jafari ◽  
Amir Mahdi Abdolhosseini-Qomi ◽  
Masoud Asadpour ◽  
Maseud Rahgozar ◽  
Naser Yazdani

AbstractThe entities of real-world networks are connected via different types of connections (i.e., layers). The task of link prediction in multiplex networks is about finding missing connections based on both intra-layer and inter-layer correlations. Our observations confirm that in a wide range of real-world multiplex networks, from social to biological and technological, a positive correlation exists between connection probability in one layer and similarity in other layers. Accordingly, a similarity-based automatic general-purpose multiplex link prediction method—SimBins—is devised that quantifies the amount of connection uncertainty based on observed inter-layer correlations in a multiplex network. Moreover, SimBins enhances the prediction quality in the target layer by incorporating the effect of link overlap across layers. Applying SimBins to various datasets from diverse domains, our findings indicate that SimBins outperforms the compared methods (both baseline and state-of-the-art methods) in most instances when predicting links. Furthermore, it is discussed that SimBins imposes minor computational overhead to the base similarity measures making it a potentially fast method, suitable for large-scale multiplex networks.


Author(s):  
Abouzid Houda ◽  
Chakkor Otman

Blind source separation is a very known problem which refers to finding the original sources without the aid of information about the nature of the sources and the mixing process, to solve this kind of problem having only the mixtures, it is almost impossible , that why using some assumptions is needed in somehow according to the differents situations existing in the real world, for exemple, in laboratory condition, most of tested algorithms works very fine and having good performence because the  nature and the number of the input signals are almost known apriori and then the mixing process is well determined for the separation operation.  But in fact, the real-life scenario is much more different and of course the problem is becoming much more complicated due to the the fact of having the most of the parameters of the linear equation are unknown. In this paper, we present a novel method based on Gaussianity and Sparsity for signal separation algorithms where independent component analysis will be used. The Sparsity as a preprocessing step, then, as a final step, the Gaussianity based source separation block has been used to estimate the original sources. To validate our proposed method, the FPICA algorithm based on BSS technique has been used.


2020 ◽  
pp. 1237-1247
Author(s):  
Xiangdong Wang ◽  
Yang Yang ◽  
Hong Liu ◽  
Yueliang Qian ◽  
Duan Jia

In real world applications of speech recognition, recognition errors are inevitable, and manual correction is necessary. This paper presents an approach for the refinement of Mandarin speech recognition result by exploiting user feedback. An interface incorporating character-based candidate lists and feedback-driven updating of the candidate lists is introduced. For dynamic updating of candidate lists, a novel method based on lattice modification and rescoring is proposed. By adding words with similar pronunciations to the candidates next to the corrected character into the lattice and then performing rescoring on the modified lattice, the proposed method can improve the accuracy of the candidate lists even if the correct characters are not in the original lattice, with much lower computational cost than that of the speech re-recognition methods. Experimental results show that the proposed method can reduce 24.03% of user inputs and improve average candidate rank by 25.31%.


2020 ◽  
Vol 270 ◽  
pp. 115061 ◽  
Author(s):  
Liliane Ableitner ◽  
Verena Tiefenbeck ◽  
Arne Meeuw ◽  
Anselma Wörner ◽  
Elgar Fleisch ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document