Knowledge graphs(KGs)play a pivotal role in various real-world applications,but they are frequently plagued by incomplete information,which manifests in the form of missing entities.Link prediction,which aims to infer...Knowledge graphs(KGs)play a pivotal role in various real-world applications,but they are frequently plagued by incomplete information,which manifests in the form of missing entities.Link prediction,which aims to infer missing entities given existing facts,has been mostly addressed by maximizing the likelihood of observed triplets at the instance level.However,they ignore the semantic information most KGs contain and the prior knowledge implied by the semantic information.To address this limitation,we propose a Type-Augmented Link Prediction(TALP)approach,which builds a hierarchical feature model,computes type feature weights,trains them to be specific to different relations,encodes weights into prior probabilities and convolutional encodes instance-level information into likelihood probabilities;finally,combining them via Bayes rule to compute the posterior probabilities of entity prediction.Our proposed TALP approach achieves significantly better performance than existing methods on link prediction benchmark datasets.展开更多
The single safety factor criteria for slope stability evaluation, derived from the rigid limit equilibrium method or finite element method （FEM）, may not include some important information, especially for steep slop...The single safety factor criteria for slope stability evaluation, derived from the rigid limit equilibrium method or finite element method （FEM）, may not include some important information, especially for steep slopes with complex geological conditions. This paper presents a new reliability method that uses sample weight analysis. Based on the distribution characteristics of random variables, the minimal sample size of every random variable is extracted according to a small sample t-distribution under a certain expected value, and the weight coefficient of each extracted sample is considered to be its contribution to the random variables. Then, the weight coefficients of the random sample combinations are determined using the Bayes formula, and different sample combinations are taken as the input for slope stability analysis. According to one-to-one mapping between the input sample combination and the output safety coefficient, the reliability index of slope stability can be obtained with the multiplication principle. Slope stability analysis of the left bank of the Baihetan Project is used as an example, and the analysis results show that the present method is reasonable and practicable for the reliability analysis of steep slopes with complex geological conditions.展开更多
The feature of finite state Markov channel probability distribution is discussed on condition that original I/O are known. The probability is called posterior condition probability. It is also proved by Bayes formula ...The feature of finite state Markov channel probability distribution is discussed on condition that original I/O are known. The probability is called posterior condition probability. It is also proved by Bayes formula that posterior condition probability forms stationary Markov sequence if channel input is independently and identically distributed. On the contrary, Markov property of posterior condition probability isn’t kept if the input isn’t independently and identically distributed and a numerical example is utilized to explain this case. The properties of posterior condition probability will aid the study of the numerical calculated recurrence formula of finite state Markov channel capacity.展开更多
基金This work was supported by the National Key R&DProgram of China under Grant No.2020YFB1710200.
文摘Knowledge graphs(KGs)play a pivotal role in various real-world applications,but they are frequently plagued by incomplete information,which manifests in the form of missing entities.Link prediction,which aims to infer missing entities given existing facts,has been mostly addressed by maximizing the likelihood of observed triplets at the instance level.However,they ignore the semantic information most KGs contain and the prior knowledge implied by the semantic information.To address this limitation,we propose a Type-Augmented Link Prediction(TALP)approach,which builds a hierarchical feature model,computes type feature weights,trains them to be specific to different relations,encodes weights into prior probabilities and convolutional encodes instance-level information into likelihood probabilities;finally,combining them via Bayes rule to compute the posterior probabilities of entity prediction.Our proposed TALP approach achieves significantly better performance than existing methods on link prediction benchmark datasets.
基金supported by the National Natural Science Foundation of China (Grant No. 90510017)
文摘The single safety factor criteria for slope stability evaluation, derived from the rigid limit equilibrium method or finite element method （FEM）, may not include some important information, especially for steep slopes with complex geological conditions. This paper presents a new reliability method that uses sample weight analysis. Based on the distribution characteristics of random variables, the minimal sample size of every random variable is extracted according to a small sample t-distribution under a certain expected value, and the weight coefficient of each extracted sample is considered to be its contribution to the random variables. Then, the weight coefficients of the random sample combinations are determined using the Bayes formula, and different sample combinations are taken as the input for slope stability analysis. According to one-to-one mapping between the input sample combination and the output safety coefficient, the reliability index of slope stability can be obtained with the multiplication principle. Slope stability analysis of the left bank of the Baihetan Project is used as an example, and the analysis results show that the present method is reasonable and practicable for the reliability analysis of steep slopes with complex geological conditions.
文摘The feature of finite state Markov channel probability distribution is discussed on condition that original I/O are known. The probability is called posterior condition probability. It is also proved by Bayes formula that posterior condition probability forms stationary Markov sequence if channel input is independently and identically distributed. On the contrary, Markov property of posterior condition probability isn’t kept if the input isn’t independently and identically distributed and a numerical example is utilized to explain this case. The properties of posterior condition probability will aid the study of the numerical calculated recurrence formula of finite state Markov channel capacity.
