Previous studies have revealed that both Bi doping and Bi_(2)Te_(3) alloying are successful strategies to optimize the thermoelectric performance of SnTe;however,detailed and thorough investigations on exactly how the...Previous studies have revealed that both Bi doping and Bi_(2)Te_(3) alloying are successful strategies to optimize the thermoelectric performance of SnTe;however,detailed and thorough investigations on exactly how they differ in modulating the band structure and microstructure were seldom given.Through a systematic comparison between Bi-doped and Bi_(2)Te_(3)-alloyed SnTe,we find in this work that despite the fact that they both contribute to the valence band convergence of SnTe,Bi_(2)Te_(3) alloying induces little effect on the hole concentration unlike the typical n-type feature of Bi-doping;moreover,Bi_(2)Te_(3) alloying tends to produce dense dislocation arrays at micron-scale grain boundaries which differs significantly from the substitutional point defect character upon Bi-doping.It was then found that Bi_(2)Te_(3) alloying exhibits a relatively higher quality factor(B∼μ_(w)/κ_(lat))at higher temperatures than Bi-doping.Subsequent Ge-doping in Bi_(2)Te_(3)-alloyed samples results in further valence band convergence and hole concentration optimization and eventually results in a maximum figure of merit ZT of 1.4 at 873 K in the composition of(Sn_(0.88)Ge_(0.12)Te)_(0.97)-(BiTe_(1.5))_(0.03).展开更多
Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single t...Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely studied.Early efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of behaviors.However,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of behaviors.However,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of behaviors.The limitation hinders the development of HSBR and results in unsatisfactory performance.As a response,we propose a novel behavior-aware graph neural network(BGNN)for HSBR.Our BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a session.Moreover,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified way.We then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our BGNN.An exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can easily and effectively be extended to multibehavior scenarios.展开更多
基金the financial support of the Natural Science Basic Research Plan in the Shaanxi Province of China(Grant No.2021JM-201 and 2021ZDLSF06-03)the National Natural Science Foundation of China(No.51872177 and 51901121)+2 种基金the Fundamental Research Funds for the Central Universities(Program No.GK202002014,GK202103022 and 2021TS009)the Science and Technology Project of Xi’an(Grant No.2020KJRC0014)Support from Shaanxi Sanqin Scholars Innovation Team was also appreciated.
文摘Previous studies have revealed that both Bi doping and Bi_(2)Te_(3) alloying are successful strategies to optimize the thermoelectric performance of SnTe;however,detailed and thorough investigations on exactly how they differ in modulating the band structure and microstructure were seldom given.Through a systematic comparison between Bi-doped and Bi_(2)Te_(3)-alloyed SnTe,we find in this work that despite the fact that they both contribute to the valence band convergence of SnTe,Bi_(2)Te_(3) alloying induces little effect on the hole concentration unlike the typical n-type feature of Bi-doping;moreover,Bi_(2)Te_(3) alloying tends to produce dense dislocation arrays at micron-scale grain boundaries which differs significantly from the substitutional point defect character upon Bi-doping.It was then found that Bi_(2)Te_(3) alloying exhibits a relatively higher quality factor(B∼μ_(w)/κ_(lat))at higher temperatures than Bi-doping.Subsequent Ge-doping in Bi_(2)Te_(3)-alloyed samples results in further valence band convergence and hole concentration optimization and eventually results in a maximum figure of merit ZT of 1.4 at 873 K in the composition of(Sn_(0.88)Ge_(0.12)Te)_(0.97)-(BiTe_(1.5))_(0.03).
基金support of the National Natural Science Foundation of China(Grant Nos.62172283 and 61836005).
文摘Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely studied.Early efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of behaviors.However,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of behaviors.However,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of behaviors.The limitation hinders the development of HSBR and results in unsatisfactory performance.As a response,we propose a novel behavior-aware graph neural network(BGNN)for HSBR.Our BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a session.Moreover,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified way.We then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our BGNN.An exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can easily and effectively be extended to multibehavior scenarios.
