Matrix factorization （MF） has been proved to be a very effective technique for collaborative filtering （ CF）, and hence has been widely adopted in today＇s recommender systems, Yet due to its lack of consideration...Matrix factorization （MF） has been proved to be a very effective technique for collaborative filtering （ CF）, and hence has been widely adopted in today＇s recommender systems, Yet due to its lack of consideration of the users＇ and items＇ local structures, the recommendation accuracy is not fully satisfied. By taking the trusts among users＇ and between items＇ effect on rating information into consideration, trust-aware recommendation systems （TARS） made a relatively good performance. In this paper, a method of incorporating trust into MF was proposed by building user-based and item-based implicit trust network under different contexts and implementing two implicit trust-based context-aware MF （]TMF） models. Experimental results proved the effectiveness of the methods.展开更多
It is a time-consuming and often iterative procedure to determine design parameters based on fine, accurate but expensive, models. To decrease the number of fine model evaluations, space mapping techniques may be empl...It is a time-consuming and often iterative procedure to determine design parameters based on fine, accurate but expensive, models. To decrease the number of fine model evaluations, space mapping techniques may be employed. In this approach, it is assumed both fine model and coarse, fast but inaccurate, one are available. First, the coarse model is optimized to obtain design parameters satisfying design objectives. Next, auxiliary parameters are calibrated to match coarse and fine models’ responses. Then, the improved coarse model is re-optimized to obtain new design parameters. The design procedure is stopped when a satisfactory solution is reached. In this paper, an implicit space mapping method is used to design a microstrip low-pass elliptic filter. Simulation results show that only two fine model evaluations are sufficient to get satisfactory results.展开更多
推荐系统是解决信息过载问题的核心。现有的推荐框架研究面临着显式反馈数据稀疏和数据预处理难等问题,特别是对新用户和新项目进行推荐的性能有待进一步提高。随着深度学习的推进,基于深度学习的推荐成为了当前的研究热点,大量的实验...推荐系统是解决信息过载问题的核心。现有的推荐框架研究面临着显式反馈数据稀疏和数据预处理难等问题,特别是对新用户和新项目进行推荐的性能有待进一步提高。随着深度学习的推进,基于深度学习的推荐成为了当前的研究热点,大量的实验证明了深度学习运用于推荐系统的有效性。文中在NCF的基础上提出了EANCF(Neural Collaborative Filtering based on Enhanced-Attention Mechanism),从隐式反馈数据的角度研究了推荐框架,利用最大池化、局部推理以及组合多种不同数据融合方式来考虑数据特征提取;同时,引入注意力机制来为网络合理地分配权重值,减少信息的损失,提升推荐的性能。最后,基于两个大型真实数据集Movielens-1m和Pinterest-20对EANCF、NCF和部分经典算法做了对比实验,并且详细地给出了EANCF框架的训练过程。实验结果表明,EANCF框架确实具有较好的推荐性能,相比于NCF框架在HR@10和NDCG@10上均有显著提升,HR@10最高提升了3.53%,NDCG@10最高提升了2.47%。展开更多
文摘Matrix factorization （MF） has been proved to be a very effective technique for collaborative filtering （ CF）, and hence has been widely adopted in today＇s recommender systems, Yet due to its lack of consideration of the users＇ and items＇ local structures, the recommendation accuracy is not fully satisfied. By taking the trusts among users＇ and between items＇ effect on rating information into consideration, trust-aware recommendation systems （TARS） made a relatively good performance. In this paper, a method of incorporating trust into MF was proposed by building user-based and item-based implicit trust network under different contexts and implementing two implicit trust-based context-aware MF （]TMF） models. Experimental results proved the effectiveness of the methods.
文摘It is a time-consuming and often iterative procedure to determine design parameters based on fine, accurate but expensive, models. To decrease the number of fine model evaluations, space mapping techniques may be employed. In this approach, it is assumed both fine model and coarse, fast but inaccurate, one are available. First, the coarse model is optimized to obtain design parameters satisfying design objectives. Next, auxiliary parameters are calibrated to match coarse and fine models’ responses. Then, the improved coarse model is re-optimized to obtain new design parameters. The design procedure is stopped when a satisfactory solution is reached. In this paper, an implicit space mapping method is used to design a microstrip low-pass elliptic filter. Simulation results show that only two fine model evaluations are sufficient to get satisfactory results.
文摘推荐系统是解决信息过载问题的核心。现有的推荐框架研究面临着显式反馈数据稀疏和数据预处理难等问题,特别是对新用户和新项目进行推荐的性能有待进一步提高。随着深度学习的推进,基于深度学习的推荐成为了当前的研究热点,大量的实验证明了深度学习运用于推荐系统的有效性。文中在NCF的基础上提出了EANCF(Neural Collaborative Filtering based on Enhanced-Attention Mechanism),从隐式反馈数据的角度研究了推荐框架,利用最大池化、局部推理以及组合多种不同数据融合方式来考虑数据特征提取;同时,引入注意力机制来为网络合理地分配权重值,减少信息的损失,提升推荐的性能。最后,基于两个大型真实数据集Movielens-1m和Pinterest-20对EANCF、NCF和部分经典算法做了对比实验,并且详细地给出了EANCF框架的训练过程。实验结果表明,EANCF框架确实具有较好的推荐性能,相比于NCF框架在HR@10和NDCG@10上均有显著提升,HR@10最高提升了3.53%,NDCG@10最高提升了2.47%。
