Hadi Daneshmand 1 / 3 RESEARCH STATEMENT

Past Researches: Diffusion of virus in computer networks, information cascade in social networks, cascade failure on networks, diffusion of diseases between peoples are samples of diffusion on complex networks. Actually, diffusion or cascade is a general term for transmission trough links which is established among persons or objects. Mathematical modeling of this transmission process provides a cascade model which is distinctive to the context and type of the network. In particular, continuous time diffusion model [5] is a diffusion model that proposed to model diffusion process in a social network. In fact, my research course lies in inference network structure by time of infection based on continuous time diffusion model. In some applications network structure is not available and only infection time of network nodes are available. For instance, in viral marketing we have only time of purchasing a product. Furthermore, peoples don’t mention reference of posts in many information sources such as web logs [8]. Link Prediction in Signed Social Networks Based on Interaction of Different Cascade Types: In some networks, relationships are signed means there are cooperation relationships (positive links) and competition relationships (negative links) among the nodes. The central premise of the signed links is that negative links cause opposite actions and behaviours [7]. As initial course of research, I tried to infer missed signed structure [3], thereby simulating two different types of diffused information. Consequently, I have proposed an extended version of NETRATE [5] method, as an efficient method to predict hidden structure using temporal dynamic, to predict sign of relationships, along with the unknown structure [3]. A Time-aware Recommender System based on Dependency Network of Items: Designing a recommendation method using cascade in signed structure was my second research topic. High and low rates of some items, which reflect users’ satisfaction, contributes elements of a collaborative filtering as a technique of designing a recommender system. From a novel point of view, there might be a hidden signed structure between items on which each user creates cascade sequence of low and high rates. Therefore, signed structure estimated by users’ rates history, i.e. time of high and low rates, would be handy for prediction of future desires of a user [4]. Estimating Diffusion Network Structures: Recovery Conditions, Sample Complexity Soft-thresholding Algorithm; Can we infer true structure of the network by infinite number of cascades? How many sampled cas-