Graphs and networks are very common data structure for modelling complex systems that are composed of a number of nodes and topologies, such as social networks, citation networks, biological protein-protein interactions networks, etc. In recent years, machine learning has become an efficient technique to obtain representation of graph for downstream graph analysis tasks, including node classification, link prediction, and community detection. Different with traditional graph analytical models, the representation learning on graph tries to learn low dimensional embeddings by means of machine learning models that could be trained in supervised, unsupervised or semi-supervised manners. Compared with traditional approaches that directly use input node attributes, these embeddings are much more informative and helpful for graph analysis. There are a number of developed models in this respect, that are different in the ways of measuring similarity of vertexes in both original space and feature space. In order to learn more efficient node representation with better generalization property, we propose a task-independent graph representation model, called as graph deconvolutional network (GDN), and corresponding unsupervised learning algorithm in this paper. Different with graph convolution network (GCN) from the scratch, which produces embeddings by convolving input attribute vec- tors with learned filters, the embeddings of the proposed GDN model are desired to be convolved with filters so that reconstruct the input node attribute vectors as far as possible. The embeddings and filters are alternatively optimized in the learning procedure. The correctness of the proposed GDN model is verified by multiple tasks over several datasets. The experimental results show that the GDN model outperforms existing alternatives with a big margin
Keywords: graph representation | representation learning | unsupervised learning |node embedding | machine learning

Link prediction has been becoming an important research topic due to the rapid growth of social networks. Community-based link prediction methods are proposed to incorporate community information in order to achieve accurate prediction. However, the performance of such methods is sensitive to the selection of community detection algorithms, and they also fail to capture the correlation between link formulation and community evolution. In this paper we introduce a balanced Modularity-Maximization Link Prediction (MMLP) model to address this issue. The idea of MMLP is to integrate the formulation of two types of links into a partitioned network generative model. We proposed a probabilistic algo rithm to emphasize the role of innerLinks, which correspondingly maximizes the network modularity. Then, a trade-off technique is designed to maintain the network in a stable state of equilibrium. We also present an effective feature aggregation method by exploring two variations of network features. Our proposed method can overcome the limit of sev eral community-based methods and the extensive experimental results on both synthetic and real-world benchmark data demonstrate its effectiveness and robustness.
Keywords: Link prediction | Social network | Community detection | Modularity

The market performance prediction of domestic motion picture is an important problem that is worthy of study. In this paper, by incorporating Chinese fine-grained semantic fea tures, we propose a method of community detection and genetic optimization especially for Chinese domestic films. These semantic features, also named as gene elements, are used as nodes to construct a movie complex network. Through leveraging the influence of the node both in the whole network and in the internal community, four unique commu nities are revealed for successful Chinese movies. Then the Genetic Algorithm (GA) with a proposed novel fitness function is used to obtain the optimal cluster of gene elements. For the other operations in GA (i.e. initialization, selection, crossover and mutation), the pa rameters are also be optimized by a distinctive evaluation method. Finally, the experiments on the data of Chinese motion pictures in 2016 demonstrate the efficacy and accuracy of the overall system.
Keywords: Semantic feature | Movie complex network | Community detection | Genetic algorithm

It is commonly agreed that data (and data-centric services) will be one of the cornerstones of Future Internet systems. In this context, mobile Opportunistic Networks (OppNets) are one of the key paradigms to efficiently support, in a self-organising and decentralised manner, the growth of data generated by localized interactions between users mobile devices, and between them and nearby smart devices such as IoT nodes. In OppNets scenarios, the spontaneous collaboration among mobile devices is exploited to disseminate data toward interested users. However, the limited resources and knowledge available at each node, and the vast amount of data available in the network, make it difficult to devise efficient schemes to accomplish this task. Recent solutions propose to equip each device with data filtering methods derived from human information processing schemes, known as Cognitive Heuristics. They are very effective methods used by human brains to quickly drop useless information and keep only the most relevant information. Althought cognitive-based OppNet solutions proved to be efficient (with limited overheads), they can become less effective when facing dynamic scenarios or situations where nodes cannot fully collaborate with each other, as we show in this paper. One of the reasons is that the solutions proposed so far do not take take into account the social structure of the environment where the nodes are moving in. In order to be more effective, the selection of information performed by each node should take into consideration not only the relevance of content for the local device, but also for other devices will encounter in the future due to mobility. To this end, in this paper we propose a social-based data dissemination scheme, based on a cognitive heuristic, known as the Social Circle Heuristic. This heuristic is an evaluation method that exploits the structure of the social environment to make inferences about the relevance of discovered information. We show how the Social Circle Heuristic, coupled with a cognitive-based community detection scheme, can be exploited to design an effective data dissemination algorithm for OppNets. We provide a detailed analysis of the performance of the proposed solution via simulation.
Keywords: Opportunistic Networks | Cognitive Heuristics | Data Dissemination | Social | Self-Organising