Xiaojun Ye

Bio: Xiaojun Ye is an academic researcher from Tsinghua University. The author has contributed to research in topics: Differential privacy & Workflow. The author has an hindex of 11, co-authored 63 publications receiving 511 citations.

Requirements model driven adaption and evolution of Internetware

Abstract: Today’s software systems need to support complex business operations and processes. The development of the web-based software systems has been pushing up the limits of traditional software engineering methodologies and technologies as they are required to be used and updated almost real-time, so that users can interact and share the same applications over the internet as needed. These applications have to adapt quickly to the diversified and dynamic changing requirements in the physical, technological, economical and social environments. As a consequence, we are expecting a major paradigm shift in software engineering to reflect such changes in computing environment in order to better address the fundamental needs of organisations in this new era. Existing software technologies, such as model driven development, business process engineering, online (re-)configuration, composition and adaptation of managerial functionalities are being repurposed to reduce the time taken for software development by reusing software codes. The ability to dynamically combine contents from numerous web sites and local resources, and the ability to instantly publish services worldwide have opened up entirely new possibilities for software development. In retrospect to the ten years applied research on Internetware, we have witnessed such a paradigm shift, which brings about many changes to the developmental experience of conventional web applications. Several related technologies, such as cloud computing, service computing, cyber-physical systems and social computing, have converged to address this emerging issue with emphasis on different aspects. In this paper, we first outline the requirements that the Internetware software paradigm should meet to excel at web application adaptation; we then propose a requirement model driven method for adaptive and evolutionary applications; and we report our experiences and case studies of applying it to an enterprise information system. Our goal is to provide high-level guidelines to researchers and practitioners to meet the challenges of building adaptive industrial-strength applications with the spectrum of processes, techniques and facilities provided within the Internetware paradigm.

Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions

Abstract: Though widely utilized for facilitating image management, user-provided image tags are usually incomplete and insufficient to describe the whole semantic content of corresponding images, resulting in performance degradations in tag-dependent applications and thus necessitating effective tag completion methods. In this paper, we propose a novel scheme denoted as LSR for automatic image tag completion via image-specific and tag-specific Linear Sparse Reconstructions. Given an incomplete initial tagging matrix with each row representing an image and each column representing a tag, LSR optimally reconstructs each image (i.e. row) and each tag (i.e. column) with remaining ones under constraints of sparsity, considering image-image similarity, image-tag association and tag-tag concurrence. Then both image-specific and tag-specific reconstruction values are normalized and merged for selecting missing related tags. Extensive experiments conducted on both benchmark dataset and web images well demonstrate the effectiveness of the proposed LSR.

Multiple Source Detection without Knowing the Underlying Propagation Model

Abstract: Information source detection, which is the reverse problem of information diffusion, has attracted considerable research effort recently. Most existing approaches assume that the underlying propagation model is fixed and given as input, which may limit their application range. In this paper, we study the multiple source detection problem when the underlying propagation model is unknown. Our basic idea is source prominence, namely the nodes surrounded by larger proportions of infected nodes are more likely to be infection sources. As such, we propose a multiple source detection method called Label Propagation based Source Identification (LPSI). Our method lets infection status iteratively propagate in the network as labels, and finally uses local peaks of the label propagation result as source nodes. In addition, both the convergent and iterative versions of LPSI are given. Extensive experiments are conducted on several real-world datasets to demonstrate the effectiveness of the proposed method.

DeepDirect: Learning Directions of Social Ties with Edge-Based Network Embedding

Abstract: There is a lot of research work on social ties, few of which is about the directionality of social ties. However, the directionality is actually a basic but important attribute of social ties. In this paper, we present a supervised learning problem, the tie direction learning (TDL) problem, which aims to learn the directionality function of directed social networks. Two ways are introduced to solve the TDL problem: one is based on hand-crafted features and the other, named DeepDirect , learns the social tie representation through the topological information of the network. In DeepDirect , a novel network embedding approach, which directly maps the social ties to low-dimensional embedding vectors by deep learning techniques, is proposed. DeepDirect embeds the network considering three different aspects: preserving network topology, utilizing labeled data, and generating pseudo-labels based on observed directionality patterns. Two novel applications are proposed for the learned directionality function, i.e., direction discovery on undirected ties and direction quantification on bidirectional ties. Experiments are conducted on five different real-world data sets about these two tasks. The experimental results demonstrate our methods, especially DeepDirect , are effective and promising.

RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding.

Abstract: Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose a novel semi-supervised network embedding method, termed Relaxed Similarity and Dissimilarity Network Embedding (RSDNE). Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. Experimental results on several real-world datasets demonstrate the superiority of the proposed method.

Network Representation Learning: A Survey

Abstract: With the widespread use of information technologies, information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the structure of societies, information diffusion, and communication patterns. In reality, however, the large scale of information networks often makes network analytic tasks computationally expensive or intractable. Network representation learning has been recently proposed as a new learning paradigm to embed network vertices into a low-dimensional vector space, by preserving network topology structure, vertex content, and other side information. This facilitates the original network to be easily handled in the new vector space for further analysis. In this survey, we perform a comprehensive review of the current literature on network representation learning in the data mining and machine learning field. We propose new taxonomies to categorize and summarize the state-of-the-art network representation learning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies. We summarize evaluation protocols used for validating network representation learning including published benchmark datasets, evaluation methods, and open source algorithms. We also perform empirical studies to compare the performance of representative algorithms on common datasets, and analyze their computational complexity. Finally, we suggest promising research directions to facilitate future study.

Mathematics of Operations Research.

Abstract: : This report briefly summarizes research on the following topics: game theory and energy; scheduling of large research and development programs; bimatrix games; cost/benefit analyses; measures of worth of weapons systems; hybrid primal algorithm; branch and round algorithm. A listing of papers prepared and published is included. (Author)