Abstract Deep learning on graphs, specifically graph convolutional networks (GCNs), has exhibited exceptional efficacy in the domain of recommender systems. Most GCNs have a message-passing architecture that enables nodes to aggregate information from neighbours iteratively through multiple layers. This enables GCNs to learn from higher-order information, but the model does not allow for direct captions of the local structural patterns. Our rationale is to investigate the effectiveness of capturing such local patterns for graph-based collaborative filtering to enhance model’s learning ability per layer. This technique combines lower-order and higher-order interactions during layer-wise propagation. In this paper, we propose MotifGCN to aggregate both lower-order and higher-order information in each graph convolution layer. Specifically, we develop dedicated algorithms of generating motif adjacency matrices. The matrices are then used for motif-enhanced neighbourhood aggregation in each layer. As this paper focuses on recommender systems, MotifGCN is built on the basis of bipartite graphs. Our experiments on four real-world datasets show that MotifGCN has a superior performance compared to various state-of-the-art methods.

By leveraging IoT data, Business Process Management (BPM) systems can sense the physical world situation and make more accurate decisions proactively, but the current BPM systems lack the effective method to take good use of IoT data. In this paper, a situation-aware dynamic binding method for IoT services targeting proactive BPM is proposed to meet this requirement. The method first establishes a prediction model to predict the bindable IoT services under given situations by constructing an encoder-decoder structure network model using bi-directional gated recurrent units (Bi-GRU) and incorporating an attention mechanism. Then our method creates a Dynamic IoT Service Task (DIT) model for BPM. This enables the BPM system to integrate the prediction model with dynamic switching of IoT services and a parallel running architecture for multiple IoT services. A prototype system is developed and a case study is conducted to evaluate the performance of the method. The study focuses on the safety supervision scenario for the transportation of hazardous Liquefied Natural Gas (LNG) by sea. Results show that the prediction model proposed in this paper outperforms other models on multiple indicators. Also, the case study and experimental results verify the effectiveness of the method.

With the development of IoT and AI, better knowledge and information can be learned and extracted from IoT sensory data which enables business systems to proactively provide services to customers. This paper is the first study that attempts to forecast high-level business events from raw IoT sensory event data to improve the proactivity of services and applications. We propose a deep learning based business event forecasting framework, i.e., IoT2BE, which extracts prior knowledge to identify business events from IoT sensory data, extracts features in multi-views including the spatial and temporal view, generates spatio-temporal business event embeddings, and uses a seq2seq model with attention to predict the future business events. Extensive experiments are based on two datasets including one real-world maritime ship trajectory dataset and one publicly available raw sensor dataset from a smart home environment. The results demonstrate that our framework can be effectively applied in various business scenarios.

The rapid development of web services has made it increasingly challenging for developers to find desired web services. To address this issue, researchers have developed various powerful models for service recommender systems. Recently, graph neural networks have shown promising performance in various deep learning tasks including service recommendation. This paper proposes a novel graph neural network for web service recommendation using a hierarchical attention mechanism that combines a node-level and a motif-level attention mechanisms. The node-level attention mechanism is responsible for aggregating information by the importance of different neighbors, while the motif-level attention mechanism performs a weighted combination of the node embeddings generated from different motif adjacency matrices. Finally, the generated node embeddings are optimized by the multi-layer perceptron (MLP), which in turn provide recommendations. Experimental results on real-world datasets demonstrate that our proposed model outperforms state-of-the-art approaches. Additionally, we conduct a model analysis to investigate the importance of different motifs. Overall, our proposed method shows promising performance for web service recommendation and highlights the potential of using graph neural networks in this domain.

Deep Neural Networks (DNN) based collaborative filtering has been successful in recommending services by effectively generalizing graph-structured data. However, most existing approaches focus on first-order interactions. Although recent approaches have utilized high-order connectivity, they still limit themselves to simple interactions and ignore the pattern of structural sub-graphs/motifs. In this study, we first explore the commonly used motifs in the Mashup-API interaction bipartite graph and propose a dedicated algorithm to generate the motif adjacency matrix. We then propose a Motif-based Graph Attention Network for service recommendation (MGSR) that utilizes a motif-based attention mechanism to capture the high-order information of various motifs, and a Collaborative Filtering model to generate the recommendation prediction. We have conducted extensive experiments on ProgrammableWeb dataset and our results demonstrate the superior performance of our proposed framework over some state-of-the-art approaches.

Despite the continual increase in the number of Web-APIs available on the internet, it is still challenging for API consumers to discover appropriate Web-APIs that could satisfy requirements. One of the main reasons for this is that Web-APIs registered on online directories such as ProgrammableWeb are in general isolated, as they are registered by diverse providers independently and progressively, ignoring continuous interactions among these APIs, which could enhance their discoverability. In this paper, we propose a method for analyzing the Web service ecosystem, and a complex network-based approach for constructing evolving networks for Web-APIs that are capable of enhancing their discoverability. We first conduct a two-phase analysis: We investigate mashups and Web-APIs interactions in the service ecosystem, and analyze their popularity distributions, and quantitatively measure two key node attachment dimensions within the ecosystem: Preferential Attachment and Similarity. Based on the analysis, we propose two methods for constructing evolving Web-API networks using the theoretical procedures of theBarab asi-Albert and the Popularity-SimilarityOptimizationnetwork models. Finally, we comprehensively evaluate the networks and map their properties with service discoverability using the ProgrammableWeb datasets. The results presented in this work will serve as a practical guide for designing a complex network-based solution for Web-API discovery.

Many cross-domain and cross-region services and applications have flooded the Internet, such as API services, IoT services, etc. These services are interconnected and form a new service ecosystem, the Internet of Services (IoS). Through IoS, service providers have a broader platform to deliver their services to users. Users can ask for a composite service solution without finding multiple suitable services themselves. However, IoS requires a standard modeling language and methodology to provide developers with a unified understanding of IoS. This modeling methodology should guide developers through the IoS modeling task. Therefore, we propose an Open System Architecture for the Internet of Services (IoS-OSA). We divide IoS into a three-dimensional cube according to layers, views, and lifecycle dimensions, with 64 different views. It integrates the existing scattered work of IoS into a unified framework and introduces the content description and the recommended modeling specification of each view. Finally, we propose the corresponding modeling methods for several key views in IoS-OSA such as service ecosystem, value/quality/capability (VQC) of IoS, etc., which improve the overall architecture of IoS.

By leveraging IoT Big Data, BPM can gain real-time physical world information to make faster and more accurate decisions, but there is a technical gap between IoT sensors and businesses. To bridge the gap, an event penetration mechanism from IoT sensors to business processes is proposed along a practical case study. This paper presents a concrete IoT-BPM application case dealing with seaborne safety ensurance in transporting liquefied natural gas (LNG), analyzes its technical challenges, and examines the feasibility and supposed effects of the BRIBOT approach.

In this paper, we describe PACOL (Panoramic-Collaboration), a decentralized and multi-layered architecture of runtime environment for service collaboration. We illustrate by a case study why it is designed as a decentralized control architecture, and why it is designed to support multi-tenants and service solution evolution and continuous optimization. Preliminary case analysis indicates that PACOL could be a feasible proposition to realise cross-domain, reliable and optimized service collaboration for service collaboration towards Internet of Services.

With the increasing abundance of traffic data from sensors and devices, the integration and analysis of such streaming data are gaining importance in many application scenarios. This paper proposes a service-based approach for integrating and analyzing the traffic sensor data to support green commute in China by automatically discovering carpooling companions within a community. Our focuses are on modeling and design of the carpooling discovery services, algorithms for implementing the services, and performance enhancement when the data volume scales up. The proposed approach is verified with experiments using real-world data.

Though the existing data service mashup tools are gaining acceptance, it is still challenging for developers with no or little programming skills to develop data service mashups for dealing with situational and ad-hoc business problems. The paper focuses on interactive recommendation in which assistance is provided in a context-sensitive manner when the mashup plan can't be determined in advance. The paper analyzes the problem with a motivating scenario of mashup building for criminal investigation. Inspired by the observation that there exist dataflow patterns for certain integration functionalities, a dataflow-pattern-based recommendation framework is proposed to solve the problems. The framework can not only recommend data services by discovering similar situations, but also recommend mashup patterns and target data services. We propose a method to analyze the relationships between data services and dataflow patterns through both mining history logs and matching the input/output parameters. Further, to recommend target data services, we propose a method to transform the data mashup plans into mixed graphs and apply the graph-based substructure pattern mining (gSpan) algorithm on them. Experiments show that the dataflow-pattern-based recommendation approach for data service mashup is effective and efficient.

Cloud computing provides virtualized, dynamically-scalable computing power. At the same time, reduction of cost is also considered as an important advantage of cloud computing. Data integration can notably benefit from cloud computing because integrating data is usually an expensive task. However, existing optimization techniques pay less attention on the fact that different execution plans of the same data integration application generate different usage costs while cloud computing provides good enough performance, so this paper introduces the cost optimization of cloud-based data integration system. The data integration system's data service layer facilitates accessing and composing information from a range of enterprise data sources through data service composition. In addition, two task scheduling algorithms for parallel part and non-parallel part are proposed to minimize the usage cost required to complete the execution of composite data service when computational capability provided by cloud computing is charged. Both of the two can obtain optimal plans in polynomial time. Experiments with the system indicate that our algorithms can lead to significant cost saving over more straightforward techniques.

This paper presents an end-user-oriented programming environment called Mashroom. Major contributions herein include an end-user programming model with an expressive data structure as well as a set of formally-defined mashup operators. The data structure takes advantage of nested table, and maintains the intuitiveness while allowing users to express complex data objects. The mashup operators are visualized with contextual menu and formula bar and can be directly applied on the data. Experiments and case studies reveal that end users have little difficulty in effectively and efficiently using Mashroom to build mashup applications.