Composite Recommendation of Artworks in E-Commerce Based on User Keyword-Driven Correlation Graph Search

With the ever-increasing diversification of people’s interests and preferences,artwork has become one of the most popular commodities or investment goods in E-commerce,and it increasingly attracts the attention of the public.Currently,many real-world or virtual artworks can be found in E-commerce,and finding a means to recommend them to appropriate users has become a significant task to alleviate the heavy burden on artwork selection decisions by users.Existing research mainly studies the problem of single-artwork recommendation while neglecting the more practical but more complex composite recommendation of artworks in E-commerce,which considerably influences the quality of experience of potential users,especially when they need to select a set of artworks instead of a single artwork.Inspired by this limitation,we put forward a novel composite recommendation approach to artworks by a user keyword-driven correlation graph search named ART_(com-rec).Through ART_(com-rec),the recommender system can output a set of artworks(e.g.,an artwork composite solution)in E-commerce by considering the keywords typed by a user to indicate his or her personalized preferences.Finally,we validate the feasibility of the ART_(com-rec) approach by a set of simulated experiments on a real-world PW dataset.

Graph representation learning-based residential electricity behavior identification and energy management

It is important to achieve an efficient home energy management system(HEMS)because of its role in promoting energy saving and emission reduction for end-users.Two critical issues in an efficient HEMS are identification of user behavior and energy management strategy.However,current HEMS methods usually assume perfect knowledge of user behavior or ignore the strong correlations of usage habits with different applications.This can lead to an insuffi-cient description of behavior and suboptimal management strategy.To address these gaps,this paper proposes non-intrusive load monitoring(NILM)assisted graph reinforcement learning(GRL)for intelligent HEMS decision making.First,a behavior correlation graph incorporating NILM is introduced to represent the energy consumption behavior of users and a multi-label classification model is used to monitor the loads.Thus,efficient identification of user behavior and description of state transition can be achieved.Second,based on the online updating of the behavior correlation graph,a GRL model is proposed to extract information contained in the graph.Thus,reliable strategy under uncer-tainty of environment and behavior is available.Finally,the experimental results on several datasets verify the effec-tiveness of the proposed model.

Personalized News Recommendation Based on the Text and Image Integration

The personalized news recommendation has been very popular in the news recommendation field.In most research,the picture information in the news is ignored,but the information conveyed to the users through pictures is more intuitive and more likely to affect the users’reading interests than the one in the textual form.Therefore,in this paper,a model that combines images and texts in the news is proposed.In this model,the new tags are extracted from the images and texts in the news,and based on these new tags,an adaptive tag(AT)algorithm is proposed.The AT algorithm selects the tags the user is interested in based on the user feedback.In particular,the AT algorithm can predict tags that a user may be interested in with the help of the tag correlation graph without any user feedback.The proposed AT algorithm is verified by experiments.The experimental results verified the AT algorithm regarding three evaluation indexes F1-score(F1),area under curve(AUC)and mean reciprocal rank(MRR).The recommended effect of the proposed algorithm is found to be better than those of the various baseline algorithms on real-world datasets.

Causality Analysis of Futures Sugar Prices in Zhengzhou Based on Graphical Models for Multivariate Time Series

This paper presents a method of constructing a mixed graph which can be used to analyze the causality for multivariate time series.We construct a partial correlation graph at first which is an undirected graph.For every undirected edge in the partial correlation graph,the measures of linear feedback between two time series can help us decide its direction,then we obtain the mixed graph.Using this method,we construct a mixed graph for futures sugar prices in Zhengzhou（ZF）,spot sugar prices in Zhengzhou（ZS） and futures sugar prices in New York（NF）.The result shows that there is a bi-directional causality between ZF and ZS,an unidirectional causality from NF to ZF,but no causality between NF and ZS.

Threshold-Based Shortest Path Query over Large Correlated Uncertain Graphs

With the popularity of uncertain data, queries over uncertain graphs have become a hot topic in the database community. As one of the important queries, the shortest path query over an uncertain graph has attracted much attention of researchers due to its wide applications. Although there are some e？cient solutions addressing this problem, all existing models ignore an important property existing in uncertain graphs： the correlation among the edges sharing the same vertex. In this paper, we apply Markov network to model the hidden correlation in uncertain graphs and compute the shortest path. Unfortunately, calculating the shortest path and corresponding probability over uncertain graphs modeled by Markov networks is a #P-hard problem. Thus, we propose a filtering-and-verification framework to accelerate the queries. In the filtering phase, we design a probabilistic shortest path index based on vertex cuts and blocks of a graph. We find a series of upper bounds and prune the vertices and edges whose upper bounds of the shortest path probability are lower than the threshold. By carefully picking up the blocks and vertex cuts, the index is optimized to have the maximum pruning capability, so that we can filter a large number of vertices which make no contribution to the final shortest path query results. In the verification phase, we develop an e？cient sampling algorithm to determine the final query answers. Finally, we verify the e？ciency and effectiveness of our solutions with extensive experiments.