arXiv subjects

Qiang Guo

Publications and source records attributed to Qiang Guo.

45 records · Page 3Linked to original sources

arXiv2014

Ultra accurate collaborative information filtering via directed user similarity

A key challenge of the collaborative filtering (CF) information filtering is how to obtain the reliable and accurate results with the help of peers' recommendation. Since the similarities from small-degree users to large-degree users would be larger than the ones opposite direction, the large-degree users' selections are recommended extensively by the traditional second-order CF algorithms. By considering the users' similarity direction and the second-order correlations to depress the influence of mainstream preferences, we present the directed second-order CF (HDCF) algorithm specifically to address the challenge of accuracy and diversity of the CF algorithm. The numerical results for two benchmark data sets, MovieLens and Netflix, show that the accuracy of the new algorithm outperforms the state-of-the-art CF algorithms. Comparing with the CF algorithm based on random-walks proposed in the Ref.7, the average ranking score could reach 0.0767 and 0.0402, which is enhanced by 27.3\% and 19.1\% for MovieLens and Netflix respectively. In addition, the diversity, precision and recall are also enhanced greatly. Without relying on any context-specific information, tuning the similarity direction of CF algorithms could obtain accurate and diverse recommendations. This work suggests that the user similarity direction is an important factor to improve the personalized recommendation performance.

cs.IR↗

arXiv2012

Solving the accuracy-diversity dilemma via directed random walks

Random walks have been successfully used to measure user or object similarities in collaborative filtering (CF) recommender systems, which is of high accuracy but low diversity. A key challenge of CF system is that the reliably accurate results are obtained with the help of peers' recommendation, but the most useful individual recommendations are hard to be found among diverse niche objects. In this paper we investigate the direction effect of the random walk on user similarity measurements and find that the user similarity, calculated by directed random walks, is reverse to the initial node's degree. Since the ratio of small-degree users to large-degree users is very large in real data sets, the large-degree users' selections are recommended extensively by traditional CF algorithms. By tuning the user similarity direction from neighbors to the target user, we introduce a new algorithm specifically to address the challenge of diversity of CF and show how it can be used to solve the accuracy-diversity dilemma. Without relying on any context-specific information, we are able to obtain accurate and diverse recommendations, which outperforms the state-of-the-art CF methods. This work suggests that the random walk direction is an important factor to improve the personalized recommendation performance.

physics.data-an↗

arXiv2011

Information filtering via biased heat conduction

Heat conduction process has recently found its application in personalized recommendation [T. Zhou \emph{et al.}, PNAS 107, 4511 (2010)], which is of high diversity but low accuracy. By decreasing the temperatures of small-degree objects, we present an improved algorithm, called biased heat conduction (BHC), which could simultaneously enhance the accuracy and diversity. Extensive experimental analyses demonstrate that the accuracy on MovieLens, Netflix and Delicious datasets could be improved by 43.5%, 55.4% and 19.2% compared with the standard heat conduction algorithm, and the diversity is also increased or approximately unchanged. Further statistical analyses suggest that the present algorithm could simultaneously identify users' mainstream and special tastes, resulting in better performance than the standard heat conduction algorithm. This work provides a creditable way for highly efficient information filtering.

physics.data-an↗

arXiv2009

Improved Collaborative Filtering Algorithm via Information Transformation

In this paper, we propose a spreading activation approach for collaborative filtering (SA-CF). By using the opinion spreading process, the similarity between any users can be obtained. The algorithm has remarkably higher accuracy than the standard collaborative filtering (CF) using Pearson correlation. Furthermore, we introduce a free parameter $β$ to regulate the contributions of objects to user-user correlations. The numerical results indicate that decreasing the influence of popular objects can further improve the algorithmic accuracy and personality. We argue that a better algorithm should simultaneously require less computation and generate higher accuracy. Accordingly, we further propose an algorithm involving only the top-$N$ similar neighbors for each target user, which has both less computational complexity and higher algorithmic accuracy.

cs.LG↗

arXiv2009

Effect of user tastes on personalized recommendation

In this paper, based on a weighted projection of the user-object bipartite network, we study the effects of user tastes on the mass-diffusion-based personalized recommendation algorithm, where a user's tastes or interests are defined by the average degree of the objects he has collected. We argue that the initial recommendation power located on the objects should be determined by both of their degree and the users' tastes. By introducing a tunable parameter, the user taste effects on the configuration of initial recommendation power distribution are investigated. The numerical results indicate that the presented algorithm could improve the accuracy, measured by the average ranking score, more importantly, we find that when the data is sparse, the algorithm should give more recommendation power to the objects whose degrees are close to the users' tastes, while when the data becomes dense, it should assign more power on the objects whose degrees are significantly different from user's tastes.

physics.data-an↗

arXiv2006

Relationship Between Structural Characters and Synchronizability of Scale-free Networks

Using Memory Tabu Search(MTS) algorithm, we investigate the relationship between structural characters and synchronizability of scale-free networks by maximizing and minimizing the ratio $Q$ of the eigenvalues of the coupling matrix by edge-intercrossing procedures. The numerical results indicate that clustering coefficient $C$, maximal betweenness $B_{max}$ are two most important factors to scale-free network synchronizability, and assortative coefficient $r$ and average distance $D$ are the secondary ones. Moreover, the average degree $ $ affects the relationship between above structural characters and synchronizability of scale-free networks, and the minimal $Q$ decreases when $ $ increases.

physics.data-an↗

arXiv2006

Weighted Network of Chinese Nature Science Basic Research

Using the requisition papers of Chinese Nature Science Basic Research in management and information department, we construct the weighted network of research areas({\bf WRAN}) represented by the subject codes. In WRAN, two research areas are considered connected if they have been filled in at least one requisition paper. The edge weight is defined as the number of requisition papers which have filled in the same pairs of codes. The node strength is defined as the number of requisition papers which have filled in this code, including the papers which have filled in it only. Here we study a variety of nonlocal statistics for these networks, such as typical distances between research areas through the network, and measures of centrality such as betweenness. These statistics characteristics can illuminate the global development trend of Chinese scientific study, it is also helpful to adjust the code system to reflect the real status more accurately. Finally, we present a plausible model for the formation and structure of networks with the observed properties.

physics.soc-ph↗

arXiv2006

Growing Scale-free Small-world Networks with Tunable Assortative Coefficient

In this paper, we propose a simple rule that generates scale-free small-world networks with tunable assortative coefficient. These networks are constructed by two-stage adding process for each new node. The model can reproduce scale-free degree distributions and small-world effect. The simulation results are consistent with the theoretical predictions approximately. Interestingly, we obtain the nontrivial clustering coefficient $C$ and tunable degree assortativity $r$ by adjusting the parameter: the preferential exponent $β$. The model can unify the characterization of both assortative and disassortative networks.

physics.soc-ph↗

arXiv2005

Self-learning Mutual Selection Model for Weighted Networks

In this paper, we propose a self-learning mutual selection model to characterize weighted evolving networks. By introducing the self-learning probability $p$ and the general mutual selection mechanism, which is controlled by the parameter $m$, the model can reproduce scale-free distributions of degree, weight and strength, as found in many real systems. The simulation results are consistent with the theoretical predictions approximately. Interestingly, we obtain the nontrivial clustering coefficient $C$ and tunable degree assortativity $r$, depending on the parameters $m$ and $p$. The model can unify the characterization of both assortative and disassortative weighted networks. Also, we find that self-learning may contribute to the assortative mixing of social networks.

physics.soc-ph↗