Sequential recommendation (SR) learns from the temporal dynamics of user-item interactions to predict the next ones. Fairness-aware recommendation mitigates a variety of algorithmic biases in the learning of user preferences. This article aims at bringing a marriage between SR and algorithmic fairness. We propose a novel fairness-aware sequential recommendation task, in which a new metric, interaction fairness , is defined to estimate how recommended items are fairly interacted by users with different protected attribute groups. We propose a multi-task learning-based deep end-to-end model, FairSR, which consists of two parts. One is to learn and distill personalized sequential features from the given user and her item sequence for SR. The other is fairness-aware preference graph embedding (FPGE). The aim of FPGE is two-fold: incorporating the knowledge of users’ and items’ attributes and their correlation into entity representations, and alleviating the unfair distributions of user attributes on items. Extensive experiments conducted on three datasets show FairSR can outperform state-of-the-art SR models in recommendation performance. In addition, the recommended items by FairSR also exhibit promising interaction fairness.

While Wikipedia has been utilized for fact-checking and claim verification to debunk misinformation and disinformation, it is essential to either improve article quality and rule out noisy articles. Self-contradiction is one of the low-quality article types in Wikipedia. In this work, we propose a task of detecting self-contradiction articles in Wikipedia. Based on the "self-contradictory" template, we create a novel dataset for the self-contradiction detection task. Conventional contradiction detection focuses on comparing pairs of sentences or claims, but self-contradiction detection needs to further reason the semantics of an article and simultaneously learn the contradiction-aware comparison from all pairs of sentences. Therefore, we present the first model, Pairwise Contradiction Neural Network (PCNN), to not only effectively identify self-contradiction articles, but also highlight the most contradiction pairs of contradiction sentences. The main idea of PCNN is two-fold. First, to mitigate the effect of data scarcity on self-contradiction articles, we pre-train the module of pairwise contradiction learning using SNLI and MNLI benchmarks. Second, we select top-K sentence pairs with the highest contradiction probability values and model their correlation to determine whether the corresponding article belongs to self-contradiction. Experiments conducted on the proposed WikiContradiction dataset exhibit that PCNN can generate promising performance and comprehensively highlight the sentence pairs the contradiction locates.

Sequential recommendation (SR) is to accurately recommend a list of items for a user based on her current accessed ones. While new-coming users continuously arrive in the real world, one crucial task is to have inductive SR that can produce embeddings of users and items without re-training. Given user-item interactions can be extremely sparse, another critical task is to have transferable SR that can transfer the knowledge derived from one domain with rich data to another domain. In this work, we aim to present the holistic SR that simultaneously accommodates conventional, inductive, and transferable settings. We propose a novel deep learning-based model, Relational Temporal Attentive Graph Neural Networks (RetaGNN), for holistic SR. The main idea of RetaGNN is three-fold. First, to have inductive and transferable capabilities, we train a relational attentive GNN on the local subgraph extracted from a user-item pair, in which the learnable weight matrices are on various relations among users, items, and attributes, rather than nodes or edges. Second, long-term and short-term temporal patterns of user preferences are encoded by a proposed sequential self-attention mechanism. Third, a relation-aware regularization term is devised for better training of RetaGNN. Experiments conducted on MovieLens, Instagram, and Book-Crossing datasets exhibit that RetaGNN can outperform state-of-the-art methods under conventional, inductive, and transferable settings. The derived attention weights also bring model explainability.

Precision psychiatry is a new research field that uses advanced data mining over a wide range of neural, behavioral, psychological, and physiological data sources for classification of mental health conditions. This study presents a computational framework for predicting sleep efficiency of insomnia sufferers. A smart band experiment is conducted to collect heterogeneous data, including sleep records, daily activities, and demographics, whose missing values are imputed via Improved Generative Adversarial Imputation Networks (Imp-GAIN). Equipped with the imputed data, we predict sleep efficiency of individual users with a proposed interpretable LSTM-Attention (LA Block) neural network model. We also propose a model, Pairwise Learning-based Ranking Generation (PLRG), to rank users with high insomnia potential in the next day. We discuss implications of our findings from the perspective of a psychiatric practitioner. Our computational framework can be used for other applications that analyze and handle noisy and incomplete time-series human activity data in the domain of precision psychiatry.

Service is about value cocreation between customers and providers. Cocreation builds on human networking: people connecting fluidly with each other as customers, providers, and resources to pursue common values. This paper develops a new analysis of service value networks, building on a previously presented hypernetwork model to study how people can scale their value cocreation up to span the entire population (domain), down to meet individual needs, and transformationally to breed new business designs. The new analysis reflects the convergence of social networks and e-commerce, and the evolution of physical products toward incorporating services to users into them (such as the apps and digital resources on the iPod, iPhone, and iPad). The hypernetwork model analyzes human networks that overlay multidimensionally, such as the Internet community itself. These properties extend the previous research results on random graphs and semiregular networks. A simulation study helps verify the hypernetworking analysis.

"Common design resources¿ refers to a wide range of practices in the field of enterprise engineering. They also include tools and knowledge for collaboration among scientists and engineers. We develop them for service science: the design of complex one-of-a-kind knowledge-intensive systems. A new method, called Modelbase, accumulates reusable models (e.g., information, mathematical, and simulation) into randomly searchable repositories, and flexibly configures them for reuse. An implementation design is provided for structuring an open and scalable database of model resources and facilitating collaboration.

Digitization of production factors, including the knowledge for knowledge workers and consumers, opens almost infinite potential to connect persons, systems, processes, enterprises, products, and services. This digital connection has ushered in computerized manufacturing, global supply chain integration, the Internet, e-commerce/business, P2P social media, and many emerging services innovation. Digital connection brings about increasingly large scale systems and applications, which present sweeping challenges to many academic disciplines. We provide an analysis for digital connection from the perspective of new services innovation. New results proposed include a formulation of new micro-economic production functions and a model for achieving economy of scale through the sharing of extended cyber-infrastructure.

New extended enterprise models such as supply chain integration and demand chain management require a new method of on-demand information exchange that extends the traditional results of a global database query. The new requirements stem from, first, the fact that the information exchange involves large numbers of enterprise databases that belong to a large number of independent organizations, and second, these databases are increasingly overlapping with real-time data sources such as wireless sensor networks and radio-frequency identification (RFID) systems. One example is the industrial push to install RFID- augmented systems to integrate enterprise information along the life cycle of a product. The new effort demands openness and scalability, and leads to a new paradigm of collaboration using all these data sources. The collaboration requires a metadata technology (for reconciling different data semantics) that works on thin computing environments (e.g., emerging sensor nodes and RFID chips) as well as on traditional databases. It also needs a new extended global query model that supports participants to offer/publish information as they see fit, not just request/subscribe what they want. This paper develops new results toward meeting these requirements.

This research investigates the requirement for proactive service delivery for heavy industrial equipment and generalizes the results into a reference model for the development of service agreements in the field. The observer-participant method was used to develop and test the model with manufacturers of gas turbines, jet engines, and locomotives. The reference model organizes the requirements for information, processes, and service offerings and provides multiple views for different types of users. The reference model can also prescribe the contents of the service agreement based on goals dictated by the service provider and the customer; thus providing for mass-customization of the service agreement.

The Software Maintenance Life Cycle Model (SMLC) was developed providing a basis to help software maintenance planning. The management framework was developed based on the SMLC concept to operationalize the model. This paper provides results from two cases to validate the model and the framework.

In some environments, it is more difficult for distributed systems to cooperate. In fact, some distributed systems are highly heterogeneous and might not readily cooperate. In order to alleviate these problems, we have developed an environment that preserves the autonomy of the local systems, while enabling distributed processing. This is achieved by: modeling the different application systems into a central knowledge base (called a Metadatabase); providing each application system with a local knowledge processor; and distributing the knowledge within these local shells. This paper is concerned with describing the knowledge decomposition process used for its distribution. The decomposition process is used to minimize the needed cooperation among the local knowledge processors, and is accomplished by "serializing" the rule execution process. A rule is decomposed into an ordered set of subrules, each of which is executed in sequence and located in a specific local knowledge processor. The goals of the decomposition algorithm are to minimize the number of subrules produced, hence reducing the time spent in communication, and to assure that the sequential execution of the subrules is "equivalent" to the execution of the original rule.

Today's enterprises typically employ multiple information systems, which are independently developed, locally administered, and different in logical or physical designs. Therefore, a fundamental challenge in enterprise information management is the sharing of information for enterprise users across organizational boundaries; this requires a global query system capable of providing on-line intelligent assistance to users. Conventional technologies, such as schema-based query languages and hard-coded schema integration, are not sufficient to solve this problem. This article develops a new approach, a “model-assisted global query system,” that utilizes an on-line repository of enterprise metadata—the Metadatabase—to facilitate global query formulation and processing with certain desirable properties such as adaptiveness and open-systems architecture. A definitional model characterizing the various classes and roles of the required metadata as knowledge for the system is presented. The significance of possessing this knowledge (via a Metadatabase) toward improving the global query capabilities available previously is analyzed. On this basis, a direct method using model traversal and a query language using global model constructs are developed along with other new methods required for this approach. It is then tested through a prototype system in a computer-integrated manufacturing (CIM) setting.

A new vision effecting adaptiveness in integrated manufacturing enterprises for the next decade is formulated. This vision has been developed on the basis of intensive research over the past nine years in Rensselaer's industry-sponsored Computer Integrated Manufacturing Program. Built from existing results in both the scientific community and industry, the proposed research agenda calls for new fundamental information technology to enable Adaptive Integrated Manufacturing Enterprises (AIME). It focuses on four major problems: (1) management of multiple systems that operate concurrently over a widely distributed network without a central controller; (2) achievement of an open systems architecture that can accommodate legacy systems as well as add new systems; (3) exploitation of object-oriented technology in production systems with the crucial ability to manage heterogeneous views and propagate changes between views; and (4) modeling of enterprise information requirements for inspection and the utilization of inspection information to create a feedback loop from production to design. These problems and approaches to their solution developed are analyzed.>

The core structure of a metadatabase system for information integration in heterogeneous and distributed environments, the global information resources dictionary (GIRD) model for unified metadata representation and management (both data and knowledge), is discussed. Overviews of metadatabase systems and the two-stage entity relationship (TSER) representation method are presented. To illustrate some major properties of the metadatabase model, and to show how the GIRD elements fit together to deliver these properties, manufacturing information management examples are given. The GIRD and the information resources dictionary system (IRDS) standard are compared.>

An information modeling and design approach using a metadatabase framework and a two-stage entity-relationship (TSER) methodology to address the system integration problem is presented. The metadatabase framework is a simplification design entailing a federated system architecture, an integrated information model, and a knowledge-based control methodology. The TSER methodology, used for the information model, features both a semantic modeling construct encompassing the US Air Force's IDEF approach and an operational modeling construct for consolidating data structures across the manufacturing facility. Preliminary results of a pilot study, including both modeling and software system development, are included to illustrate the theoretical work.>

Information integration is a driving force underlying many major efforts in manufacturing systems, ranging from MRP and MRP II to the current research on CIM. The problem of integration, however, has not been sufficiently studied previously from the perspective of information. The authors analyze the information aspects of the evolution of integrating manufacturing planning with its control. A conceptual framework is developed to help identify the potentials and requirements of information integration. The strengths and limitations of MRP II are discussed in the light of the framework, leading to a formulation of further integration. A modeling methodology using this framework is also suggested.>