Predicting the potential relations between nodes in networks, known as link prediction, has long been a challenge in network science. However, most studies just focused on link prediction of static network, while real-world networks always evolve over time with the occurrence and vanishing of nodes and links. Dynamic network link prediction (DNLP) thus has been attracting more and more attention since it can better capture the evolution nature of networks, but still most algorithms fail to achieve satisfied prediction accuracy. Motivated by the excellent performance of long short-term memory (LSTM) in processing time series, in this article, we propose a novel encoder-LSTM-decoder (E-LSTM-D) deep learning model to predict dynamic links end to end. It could handle long-term prediction problems, and suits the networks of different scales with fine-tuned structure. To the best of our knowledge, it is the first time that LSTM, together with an encoder-decoder architecture, is applied to link prediction in dynamic networks. This new model is able to automatically learn structural and temporal features in a unified framework, which can predict the links that never appear in the network before. The extensive experiments show that our E-LSTM-D model significantly outperforms newly proposed DNLP methods and obtain the state-of-the-art results.
5 February 2018 in IEEE Transactions on Knowledge and Data Engineering
Real-world networks feature weights of interactions, where link weights often represent some physical attributes. In many situations, to recover the missing data or predict the network evolution, we need to predict link weights in a network. In this paper, we first proposed a series of new centrality indices for links in line graph. Then, utilizing these line graph indices, as well as a number of original graph indices, we designed three supervised learning methods to realize link weight prediction both in the networks of single layer and multiple layers, which perform much better than several recently proposed baseline methods. We found that the resource allocation index (RA) plays a more important role in the weight prediction than other topological properties, and the line graph indices are at least as important as the original graph indices in link weight prediction. In particular, the success application of our methods on Yelp layered network suggests that we can indeed predict the offline co-foraging behaviors of users just based on their online social interactions, which may open a new direction for link weight prediction algorithms, and meanwhile provide insights to design better restaurant recommendation systems.
17 April 2017 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Passive indoor localization is important. Unlike active localization techniques, it does not require for users to carry measuring devices, e.g., smart phones. Thus, it is widely used in applications such as security, smart housing, object tracking, etc. However, in real-world applications, the passive localization accuracy is limited due to the environment noises, multipath effect, etc. To address those problems, in this paper, we propose to use channel state information (CSI) instead. Specifically, we make the following contributions: 1) we design a CSI-based passive indoor localization system; 2) we develop a Naive Bayes classifier enhanced with confidence level information; and 3) we demonstrate the effectiveness of our technique using real-world deployments. The experimental results show that our technique can achieve more than 86% accuracy on average and at least 15% better than the baseline Naive Bayes classifier.
Social synchrony (SS) is an emergent phenomenon in human society. People often mimic others which, over time, can result in large groups behaving similarly. Drawing from prior empirical studies of SS in online communities, here we propose a discrete network model of SS based on four attributes: 1) depth of action; 2) breadth of impact, i.e., a large number of actions are performed with a large group of people involved; 3) heterogeneity of role, i.e., people of higher degree play more important roles; and 4) lastly, emergence of phenomenon, i.e., it is far from random. We analyze our model both analytically and with simulations, and find good agreement between the two. We find this model can well explain the four characters of SS, and thus hope it can help researchers better understand human collective behavior.
Real networks feature layers of interactions and complexity. In them, different types of nodes can interact with each other via a variety of events. Examples of this complexity are task-oriented social networks (TOSNs), where teams of people share tasks towards creating a quality artifact, such as academic research papers or software development in commercial or open source environments. Accomplishing those tasks involves both work, e.g., writing the papers or code, and communication, to discuss and coordinate. Taking into account the different types of activities and how they alternate over time can result in much more precise understanding of the TOSNs behaviors and outcomes. That calls for modeling techniques that can accommodate both node and link heterogeneity as well as temporal change. In this paper, we report on methodology for finding temporal motifs in TOSNs, limited to a system of two people and an artifact. We apply the methods to publicly available data of TOSNs from 31 Open Source Software projects. We find that these temporal motifs are enriched in the observed data. When applied to software development outcome, temporal motifs reveal a distinct dependency between collaboration and communication in the code writing process. Moreover, we show that models based on temporal motifs can be used to more precisely relate both individual developer centrality and team cohesion to programmer productivity than models based on aggregated TOSNs.
5 December 2019 in IEEE Transactions on Knowledge and Data Engineering