Federated learning is a new type of artificial intelligence technology. During the training process, the client transmits model parameter information instead of local data to ensure their privacy and security. But it also incurs higher communication costs. This article proposes a new federated learning pruning method, FedADP, with the aim of adaptively determining pruning ratios for each layer in each client model without infringing on client privacy, and achieving more accurate pruning effects. Our method not only reduces communication costs during the training process, but also maintains accuracy similar to the original model. We conducted experimental validation using classic models and datasets, and evaluated our scheme and traditional federated learning scheme in terms of model accuracy, communication cost, and computational cost.

Distributed clustering based on the Gaussian mixture model (GMM) has exhibited excellent clustering capabilities in peer-to-peer (P2P) networks. However, more iterative numbers and communication overhead are required to achieve the consensus in existing distributed GMM clustering algorithms. In addition, the truth that it cannot find a closed form for the update of parameters in GMM causes the imprecise clustering accuracy. To solve these issues, by utilizing the transfer learning technique, a general transfer distributed GMM clustering framework is exploited to promote the clustering performance and accelerate the clustering convergence. In this work, each node is treated as both the source domain and the target domain, and these nodes can learn from each other to complete the clustering task in distributed P2P networks. Based on this framework, the transfer distributed expectation-maximization algorithm with the fixed learning rate is first presented for data clustering. Then, an improved version is designed to obtain the stable clustering accuracy, in which an adaptive transfer learning strategy is adopted to adjust the learning rate automatically instead of a fixed value. To demonstrate the extensibility of the proposed framework, a representative GMM clustering method, the entropy-type classification maximum-likelihood algorithm, is further extended to the transfer distributed counterpart. Experimental results verify the effectiveness of the presented algorithms in contrast with the existing GMM clustering approaches.

Collaborative multiview clustering methods can efficiently realize the view fusion by exploring complementary and consistent information among multiple views. However, these studies ignore all the differences between multiple views in fusion. In fact, in the multiview clustering, the data are diverse from view to view. The larger the difference between any two views is, the more the fusion of these views is required. Moreover, a global tradeoff parameter is generally adopted to restrain the penalty related to the disagreement of all views, which is often defined empirically. Inspired by the idea of transfer learning, a series of novel collaborative multiview clustering algorithms are proposed to tackle these challenges. In the most basic one, each view performs clustering independently and learns from others to improve its own clustering performance, in which a global learning factor is defined to control the interaction between multiple views. The fuzzy memberships are regarded as the important knowledge to provide guidance between views, and the consensus constraint is defined to ensure the consistent partitions of all views. In addition, the local adaptive learning factors between any two views instead of a global fixed one are adopted in an improved version to emphasize the difference between views, and the adjustment strategy for the learning factor is further designed to guarantee the stability of multiview clustering without the influence of initial values. Finally, to identify the significance of different views to the clustering, the extended versions are excavated with the assignment of view weights and the maximum entropy regularization technique is employed to optimize the weights. Experiments on various real-world multiview datasets verify the superiority of the presented approaches.

Drug recommendation task based on the deep learning model has been widely studied and applied in the health care field in recent years. However, the accuracy of drug recommendation models still needs to be improved. In addition, the existing recommendation models either give only one recommendation (however, there may be a variety of drug combination options in practice) or can not provide the confidence level of the recommended result. To fill these gaps, a Drug Recommendation model based on Message Propagation neural network (denoted as DRMP) is proposed in this paper. Then, the Drug-Drug Interaction (DDI) knowledge is introduced into the proposed model to reduce the DDI rate in recommended drugs. Finally, the proposed model is extended to Bayesian Neural Network (BNN) to realize multiple recommendations and give the confidence of each recommendation result, so as to provide richer information to help doctors make decisions. Experimental results on public data sets show that the proposed model is superior to the best existing models.

Accurate prediction of patients’ ICU transfer events is of great significance for improving ICU treatment efficiency. ICU transition prediction task based on Electronic Health Records (EHR) is a temporal mining task like many other health informatics mining tasks. In the EHR-based temporal mining task, existing approaches are usually unable to mine and exploit patterns used to improve model performance. This article proposes a network based on Interval Pattern-Aware, Multi-Scale Interval Pattern-Aware (MSIPA) network. MSIPA mines different interval patterns in temporal EHR data according to the short, medium, and long intervals. MSIPA utilizes the Scaled Dot-Product Attention mechanism to query the contexts corresponding to the three scale patterns. Furthermore, Transformer will use all three types of contextual information simultaneously for ICU transfer prediction. Extensive experiments on real-world data demonstrate that an MSIPA network outperforms state-of-the-art methods.

In China, with the continuous development of national health insurance policies, more and more people have joined the health insurance. How to accurately predict patients future medical treatment behavior becomes a hotspot issue. The biggest challenge in this issue is how to improve the prediction performance by modeling health insurance data with high-dimensional time characteristics. At present, most of the research is to solve this issue by using Recurrent Neural Networks (RNNs) to construct an overall prediction model for the medical visit sequences. However, RNNs can not effectively solve the long-term dependence, and RNNs ignores the importance of time interval of the medical visit sequence. Additionally, the global model may lose some important content to different groups. In order to solve these problems, we propose a Grouping and Global Attention based Time-aware Bidirectional Long Short-Term Memory (GGATB-LSTM) model to achieve medical treatment behavior prediction. The model first constructs a heterogeneous information network based on health insurance data, and uses a tensor CANDECOMP/PARAFAC decomposition method to achieve similarity grouping. In terms of group prediction, a global attention and time factor are introduced to extend the bidirectional LSTM. Finally, the proposed model is evaluated by using real dataset, and conclude that GGATB-LSTM is better than other methods.

When using the microservice architecture to build a software development knowledge base, due to the differences in the user's knowledge level, different users have different needs for knowledge, which causes the problem of unpredictable system load. This paper proposes a load prediction model based on User Knowledge Level Evolution (UKLE). We use user historical access data and user private data to build user portraits, learn the evolution law of user knowledge levels, and thus describe the diverse knowledge growth paths of users. Finally, we predict the future knowledge access trends of users. And we use a hybrid prediction model based on linear and non-linear methods to perform load prediction for service load. The final load prediction model combines the characteristics of user knowledge level evolution and a hybrid prediction model based on service historical load, which improves the model's prediction accuracy and robustness.

Electricity information tracking systems are increasingly being adopted across China. Such systems can collect real-time power consumption data from users, and provide opportunities for artificial intelligence (AI) to help power companies and authorities make optimal demand-side management decisions. In this paper, we discuss power utilization improvement in Shandong Province, China with a deployed AI application - the Power Intelligent Decision Support (PIDS) platform. Based on improved short-term power consumption gap prediction, PIDS uses an optimal power adjustment plan which enables fine-grained Demand Response (DR) and Orderly Power Utilization (OPU) recommendations to ensure stable operation while minimizing power disruptions and improving fair treatment of participating companies. Deployed in August 2018, the platform is helping over 400 companies optimize their power consumption through DR while dynamically managing the OPU process for around 10,000 companies. Compared to the previous system, power outage under PIDS through planned shutdown has been reduced from 16% to 0.56%, resulting in significant gains in economic activities.

Session-based recommendation aims to recommend the next item a user might be interested in given limited session information, e.g., only clicks are available. Existing researches usually use the RNN-based method or combine user long-term and current session interests to learn certain user preferences. However, due to the uncertainty of user behaviors and the limited behavior information, these methods may lose information of the relevant behavioral features and introduce some noise of unrelated behaviors. For online platforms, such as knowledge base platforms, these items are not isolated but connected with each other. We can use the correlation between items to capture the potential long-distance interests of the user. Therefore, in this paper, we propose a co-attention model with sequential behaviors and side information to obtain a complete representation of user's preferences. For obtaining relevant side information outside the session, we aggregate the corresponding entities and relations of each item to get the representation of the neighborhood information. Finally, extensive experiments are carried out on two real datasets, and the experimental results demonstrate the validity of our model. In particular, the proposed model performs well in cold start scenarios and is well interpreted for the recommended results.

At present, software development is an important way to make our life more convenient and intelligent. With the development of software programming, we have accumulated a lot of expert experience and common sense of domain knowledge. How to effectively organize and reuse these high-quality knowledge has become an urgent problem because reusing high-quality expert knowledge can greatly improve the efficiency of solving problems, especially for the novices of programming. When we encounter the programming problems, the usual solutions to get the answers is to query the search engines or consult the senior developers. However, these solutions have the following limitations: 1) the information in the field of software development is relatively scattered, for example, the demanded information is distributed on different websites. The developers need to query the search engine several times to get the information that they want, which is unfriendly, especially for the novices; 2) there is no such a unified organization form for the information we retrieve, and we need to process it further to get the answers, which is inefficient. To address the above limitations, we propose to build a software development knowledge graph (SoftKG) through Wikipedia taxonomy. Specifically, we propose a framework to build SoftKG based on open source knowledge communities.

Nowadays, prediction for medical treatment migration has become one of the interesting issues in the field of health informatics. This is because the medical treatment migration behavior is closely related to the evaluation of regional medical level, the rational use of medical resources, and the distribution of medical insurance. Therefore, a prediction model for medical treatment migration based on medical insurance data is introduced in this paper. First, a medical treatment graph is constructed based on medical insurance data. The medical treatment graph is a heterogeneous graph, which contains entities such as patients, diseases, hospitals, medicines, hospitalization events, and the relations between these entities. However, existing graph neural networks are unable to capture the time-series relationships between event-type entities. To this end, a prediction model based on Graph Convolutional Network (GCN) is proposed in this paper, namely, Event-involved GCN (EGCN). The proposed model aggregates conventional entities based on attention mechanism, and aggregates event-type entities based on a gating mechanism similar to LSTM. In addition, jumping connection is deployed to obtain the final node representation. In order to obtain embedded representations of medicines based on external information (medicine descriptions), an automatic encoder capable of embedding medicine descriptions is deployed in the proposed model. Finally, extensive experiments are conducted on a real medical insurance data set. Experimental results show that our model's predictive ability is better than the best models available.

Survival prediction based on health insurance data is a promising research direction, since through health insurance data, we may be able to uncover the implicit information reflecting the health status of patients. Deep learning models, especially the Recurrent Neural Networks (RNNs), are powerful tools. However, at this stage, it is often difficult to explain the semantics of the features and evolution laws learned by RNNs. Therefore, this paper proposes a survival prediction model based on graph pattern mining. First, each patient's health insurance data are built as a Heterogeneous Information Network (HIN). Then, frequent patterns are mined from these HINs and each frequent pattern is regarded as a feature, called “pattern feature”. At last, the predictive survival time is given by an improved random forest, which is able to take into account the censored data. We conducted experiments on a real health insurance data set. The experimental results show that the model has better predictive ability than the traditional survival prediction models.

With the development of health insurance, the consequent problem of health insurance fraud has become increasingly serious. Outlier detection is a common method for health insurance anomaly detection. Researchers use some prior knowledge to assume patterns and indicators of interest. However, fraud pattern is concealed and changeable. The method of mining anomalies from fixed patterns is difficult to meet the current needs. In order to overcome this limitation, this paper combines the rich expression ability of heterogeneous information networks to model the complex relationships between entities, and establish a health insurance business representation model. The paper explores all possible business patterns, interrelated business portfolio patterns and related indicators in the field of health insurance. Considering the dynamic nature of a network, anomaly mining is carried out from both horizontal and vertical perspectives. Among them, the horizontal comparison adopts a fixed time period. The vertical comparison dynamically adjusts the time period according to the frequency of occurrence of the health insurance pattern instance, and then performs indicator calculation and outlier detection. Finally, the experimental results on the real data set show that our approach can narrow the scope of professional review and find more records of possible fraud than traditional methods.

Power demand response aims to clip the peak and fill the valley of power load by interruptible load management. Its closely related to the safety and economic benefit of the power system. At present, various provinces in China have carried out the pilot work of interruptible load management. The power companies signed contracts with power users to stipulate power users to adjust the power load consumption during peak hours or in emergency situations. The singed contracts should be fair for all power users. At the same time, the specific information about the signed contracts should be protected for privacy preservation, which is a typical federated learning scenario. A fair and privacy-preserving incentive pricing model should be proposed to stimulate power uses to participate in thee interruptible load management. To this end, a power demand response incentive pricing model is proposed. Based on the multi-attribute sealed auction game, the bidding model between the power company and the power users is established. In the single bidding model, the risk of the power user's demand response is evaluated firstly. The power users could be classified into different group according to their power load characteristics. Then a user classification selection algorithm' is proposed, which enables both the power company's revenue and power user risk to be considered, and enables the selected users to achieve balanced peak clipping. A fair mechanism based on integrals is proposed to assure the fairness between all power users. The case simulations demonstrate that effectiveness of the proposed incentive pricing model.

With the development and adoption of the electricity information tracking system in China, real-time electricity consumption big data have become available to enable artificial intelligence (AI) to help power companies and the urban management departments to make demand side management decisions. We demonstrate the Power Intelligent Decision Support (PIDS) platform, which can generate Orderly Power Utilization (OPU) decision recommendations and perform Demand Response (DR) implementation management based on a short-term load forecasting model. It can also provide different users with query and application functions to facilitate explainable decision support.

In Software as a Service model, i.e. SaaS, tenants' sensitive data are stored and processed at the platform of untrusted service providers. Data privacy has become the biggest challenge hindering wider adoption of software as a service. Data combination privacy has been proposed to protect privacy of data combination through sensitive association hidden. However, this approach doesn't consider the scenario where tenants' requirements changed and customization happened. When tenants customize data schema or privacy requirements, there is a possibility that underlying physical data chunk schema collides with the privacy requirements of tenants. This paper proposed the data combination privacy preservation adjusting mechanism for data privacy leakage caused by on demand customization of software as a service. Three principles of privacy preservation adjusting mechanism are proposed. Based on the adjusting mechanism, there would no more privacy leakage than before customization during the adjusting process to the customized schema. Analysis and experiments demonstrate the corrective and effective of the data privacy preservation adjusting mechanism for software as a service.

QoS has become an important measure for web service selection. In this paper, we present an approach which can provide the approximate QoS value for users, and support finding the optimal web service. Firstly, it clusters the users based on location and network condition, then according to the QoS historical statistics of users in the same cluster, uses the linear regression algorithm to predict the QoS value based on invocation time and workload.

Clustering learners into groups according to the customized features in e-learning environment is an important step to build a personalization learning system. Though clustering e-learners is important for better cooperation between teachers and students in e-learning, it is a challenge job to group learners flexibly and exactly. Since there are already many models for the features which are used for the basis of the clustering methods, this paper proposes an improvement of Matrix-based Clustering Method which preformed efficiently without extra comparison in contrast to k-means clustering algorithm. The improvement of the Matrix-based Clustering Method proposes the concept "Agglomerate Strength" for further cluster cohesion measurement in contrast to the previous Matrix-based Clustering Method in precision. And the comparison experiments between the improvement Matrix-based Clustering Method and the other methods, i.e. the previous Matrix-based Clustering Method and K-means algorithm, are investigated. The results of experiments show that this method is feasible and efficient.