Hui-Ju Hung

Maximizing acceptance probability for active friending in online social networks

Friending recommendation has successfully contributed to the explosive growth of online social networks. Most friending recommendation services today aim to support passive friending, where a user passively selects friending targets from the recommended candidates. In this paper, we advocate a recommendation support for active friending, where a user actively specifies a friending target. To the best of our knowledge, a recommendation designed to provide guidance for a user to systematically approach his friending target has not been explored for existing online social networking services. To maximize the probability that the friending target would accept an invitation from the user, we formulate a new optimization problem, namely, Acceptance Probability Maximization (APM), and develop a polynomial time algorithm, called Selective Invitation with Tree and In-Node Aggregation (SITINA), to find the optimal solution. We implement an active friending service with SITINA on Facebook to validate our idea. Our user study and experimental results reveal that SITINA outperforms manual selection and the baseline approach in solution quality efficiently.

Scalable and bandwidth-efficient multicast for software-defined networks

Software-Defined Networking (SDN) enables flexible network resource allocations for traffic engineering, but at the same time the scalability problem becomes more serious since traffic is more difficult to be aggregated. Those crucial issues in SDN have been studied for unicast but have not been explored for multicast traffic, and addressing those issues for multicast is more challenging since the identities and the number of members in a multicast group can be arbitrary. In this paper, therefore, we propose a new multicast tree for SDN, named Branch-aware Steiner Tree (BST). The BST problem is difficult since it needs to jointly minimize the numbers of the edges and the branch nodes in a tree, and we prove that it is NP-Hard and inapproximable within k, which denotes the number of group members. We further design an approximation algorithm, called Branch Aware Edge Reduction Algorithm (BAERA), to solve the problem. Simulation results demonstrate that the trees obtained by BAERA are more bandwidth-efficient and scalable than the shortest-path trees and traditional Steiner trees. Most importantly, BAERA is computation-efficient to be deployed in SDN since it can generate a tree on massive networks in small time.

When Social Influence Meets Item Inference

Research issues and data mining techniques for product recommendation and viral marketing have been widely studied. Existing works on seed selection in social networks do not take into account the effect of product recommendations in e-commerce stores. In this paper, we investigate the seed selection problem for viral marketing that considers both effects of social influence and item inference (for product recommendation). We develop a new model, Social Item Graph (SIG), that captures both effects in the form of hyperedges. Accordingly, we formulate a seed selection problem, called Social Item Maximization Problem (SIMP), and prove the hardness of SIMP. We design an efficient algorithm with performance guarantee, called Hyperedge-Aware Greedy (HAG), for SIMP and develop a new index structure, called SIG-index, to accelerate the computation of diffusion process in HAG. Moreover, to construct realistic SIG models for SIMP, we develop a statistical inference based framework to learn the weights of hyperedges from data. Finally, we perform a comprehensive evaluation on our proposals with various baselines. Experimental result validates our ideas and demonstrates the effectiveness and efficiency of the proposed model and algorithms over baselines.

On bundle configuration for viral marketing in social networks

Prior research on viral marketing mostly focuses on promoting one single product item. In this work, we explore the idea of bundling multiple items for viral marketing and formulate a new research problem, called Bundle Configuration for SpreAd Maximization (BCSAM). Efficiently obtaining an optimal product bundle under the setting of BCSAM is very challenging. Aiming to strike a balance between the quality of solution and the computational overhead, we systematically explore various heuristics to develop a suite of algorithms, including κ-Bundle Configuration and Aggregated Bundle Configuration. Moreover, we integrate all the proposed ideas into one efficient algorithm, called Aggregated Bundle Configuration (ABC). Finally, we conduct an extensive performance evaluation on our proposals. Experimental results show that ABC significantly outperforms its counterpart and two baseline approaches in terms of both computational overhead and bundle quality.

Routing and Scheduling of Social Influence Diffusion in Online Social Networks

Owing to the rising popularity of online social networking services (OSNs), studies on social influence and its diffusion have received significant attention from the research community. Prior research has mostly studied the impact of single-hop influence diffusion and multi-hop influence broadcast in online social networks. Very little research explores the idea of guiding (routing) multi-hop social influence towards a specific target. In this paper, we motivate the needs of timely routing social influence to formulate a new optimization problem, namely, Routing And Scheduling of Target-Oriented Social Influence Diffusion (RAS-TOSID). Accordingly, we propose the Efficient Routing And Scheduling with Social and Temporal decOmposition (ERASSTO) algorithm, which finds the optimal solution to RAS-TOSID in polynomial time. We carry out a user study by implementing ERASSTO in Facebook and conduct a comprehensive evaluation on ERASSTO and alternative approaches by simulation. The result shows that ERASSTO significantly outperforms other algorithms regarding solution quality and computational efficiency.

Relay Selection for Heterogeneous Cellular Networks with Renewable Green Energy Sources

With the advance of the photovoltaic panel technology, the infrastructure equipment of cellular networks with solar energy sources has attracted extensive interests. It is expected that base stations (BSs) and relay stations (RSs) with renewable energy will play important roles in reducing the power consumption from electrical grids in future green cellular networks. Inspired by this technology trend, this paper considers a heterogeneous green cellular network, in which a part of RSs is powered by solar energy sources to represent the incremental deployment for the infrastructure with renewable energy in the near future. We formulate a new relay selection and power allocation problem with Mixed Integer Linear Programming to select solar-powered RSs and grid-powered RSs, such that the total grid power consumption is effectively minimized in decode-and-forward cooperative communication networks. We design an algorithm to derive the optimal solution, and also devise an efficient distributed algorithm to reduce the computational cost. The simulation results demonstrate that the algorithms can effectively reduce the total grid power consumption with different channel conditions, different deployments of RSs in a network, and different available power levels in solar-powered RSs. In addition, the problem model and the proposed algorithms can be extended to support hybrid energy sources.

Social Influence-Aware Reverse Nearest Neighbor Search

Business location planning, critical to success of many businesses, can be addressed by reverse nearest neighbors (RNN) query using geographical proximity to the customers as the main metric to find a store location which is the closest to many customers. Nevertheless, we argue that other marketing factors such as social influence could be considered in the process of business location planning. In this paper, we propose a framework for business location planning that takes into account both factors of geographical proximity and social influence. An essential task in this framework is to compute the “influence spread” of RNNs for candidate locations. However, excessive computational overhead and long latency hinder its feasibility for our framework. Thus, we trade storage overhead for the processing speed by precomputing and storing the social influences between pairs of customers and design a suite of algorithms based on Targeted Region-oriented strategy. Various ordering and pruning techniques have been incorporated in these algorithms to enhance the processing efficiency of our framework. Experiments also show that the proposed algorithms efficiently support the task of location planning under various parameter settings.

Query Prediction by Currently-Browsed Web Pages and Its Applications

This paper reveals the relation between a previously-browsed webpage and a query. First, we display that there are queries triggered by its previously-browsed webpage using real examples from the log. A query is triggered by a webpage means that the issued query is related to the webpage that the user had browsed before. Then an analysis is provided to show that almost 30 % of queries following a webpage are triggered. A predictor is proposed to detect the triggered queries. We also demonstrate that the predictor can be enhanced by giving previous queries as context. Finally, we show that the prediction can be applied on a query recommendation system to suggest queries for the currently-browsed web page.

Social influence-aware reverse nearest neighbor search

Business location planning, critical to success of many businesses, can be addressed by reverse nearest neighbors (RNN) query using geographical proximity to the customers as the main metric to find a store location which is the closest to many customers. Nevertheless, we argue that other marketing factors such as social influence could be considered in the process of business location planning. In this paper, we propose a framework for business location planning that takes into account both factors of geographical proximity and social influence. An essential task in this framework is to compute the “influence spread” of RNNs for candidate locations. However, excessive computational overhead and long latency hinder its feasibility for our framework. Thus, we trade storage overhead for the processing speed by precomputing and storing the social influences between pairs of customers and design a suite of algorithms based on Targeted Region-oriented strategy. Various ordering and pruning techniques have been incorporated in these algorithms to enhance the processing efficiency of our framework. Experiments also show that the proposed algorithms efficiently support the task of location planning under various parameter settings.

On Package Organization for Willingness Satisfaction in Social Networks

Studies show that both the personal preference and social tightness between friends play important roles in the decision process of activity participation for a person. Considering the preference of a person and the social tightness among friends, in this work, we formulate a new research problem, called Package Organization for Willingness satisfaction (POWA), to effectively select items into a package that can be adopted by the most users. Efficiently obtaining the optimal package and the corresponding group of users under the setting of POWA is very challenging, as we prove that POWA is NP-hard. Aiming to strike a balance between the quality of solutions and the time needed for computation, we propose algorithm Intermediate Package Organization with Social and Preference Pruning (IPOSPP) to obtain good solutions efficiently. We conduct an extensive performance evaluation on four real datasets to demonstrate the performance of the proposed algorithm.