PGCF: Perception graph collaborative filtering for recommendation

Extensive studies have fully proved the effectiveness of collaborative filtering(CF)recommen dation models based on graph convolutional networks(GCNs).As an advanced interaction encoder,however,GCN-based CF models do not differentiate neighboring nodes,which will lead to suboptimal recommendation performance.In addition,most GCN-based CF studies pay insufficient attention to the loss function and they simply select the Bayesian personalized ranking(BPR)loss function to train the model.However,we believe that the loss function is as important as the interaction encoder and deserves more attentions.To address the above issues,we propose a novel GCN-based CF model,named perception graph collaborative filtering(PGCF).Specifically,for the interaction encoder,we design a neighborhood-perception GCN to enhance the aggregation of interest-related information of the target node during the information aggregation process,while weakening the propagation of noise and irrelevant information to help the model learn better embedding representation.For the loss function,we design a margin-perception Bayesian personalized ranking(MBPR)loss function,which introduces a self-perception margin,requiring the predicted score of the user-positive sample to be greater than that of the user-negative sample,and also greater than the sum of the predicted score of the user-negative sample and the margin.The experimental results on five benchmark datasets show that PGCF is significantly superior to multiple existing CFmodels.

A two-branch multiscale spectral-spatial feature extraction network for hyperspectral image classification

In the field of hyperspectral image(HSI)classification in remote sensing,the combination of spectral and spatial features has gained considerable attention.In addition,the multiscale feature extraction approach is very effective at improving the classification accuracy for HSIs,capable of capturing a large amount of intrinsic information.However,some existing methods for extracting spectral and spatial features can only generate low-level features and consider limited scales,leading to low classification results,and dense-connection based methods enhance the feature propagation at the cost of high model complexity.This paper presents a two-branch multiscale spectral-spatial feature extraction network(TBMSSN)for HSI classification.We design the mul-tiscale spectral feature extraction(MSEFE)and multiscale spatial feature extraction(MSAFE)modules to improve the feature representation,and a spatial attention mechanism is applied in the MSAFE module to reduce redundant information and enhance the representation of spatial fea-tures at multiscale.Then we densely connect series of MSEFE or MSAFE modules respectively in a two-branch framework to balance efficiency and effectiveness,alleviate the vanishing-gradient problem and strengthen the feature propagation.To evaluate the effectiveness of the proposed method,the experimental results were carried out on bench mark HsI datasets,demonstrating that TBMSSN obtained higher classification accuracy compared with several state-of-the-art methods.

Linear dichroism and polarization controllable persistent spin helix in two-dimensional ferroelectric ZrOI_(2) monolayer

Two-dimensional ferroelectric(2D-FE)materials that characterize the spontaneous ferroelectricity down to monolayer limit and rich ferroic properties arising from FE orderings,have been extensively explored as low-dimensional sensor,electric and memory devices.In current work,group-IV transition metal oxide dihalide MOX_(2)(M=Zr and Hf,X=Cl,Br and I)monolayers have been identified as a new group of 2D-FE materials.Using the comprehensive first-principles calculations combined with finite temperature Monte Carlo(MC)and ab initio molecular dynamics(MD)simulations,we investigate the temperature stability of FE polarization and further uncover the unique properties associated with spontaneous ferroelectricity of MOX_(2) monolayers.In particular,ZrOI_(2) monolayer,a promising 2D-FE material with room temperature stable ferroelectricity,semiconducting electronic structure and optoelectronic response under visible light,offers an ideal material platform to investigate the coupling of intrinsic anisotropy,optical absorption selectivity and spin degree of freedom with 2D ferroelectricity.Typically,significant optical absorption anisotropy and giant linear dichroism effect are predicted for a 2D optical polarizer device based on ZrOI_(2) monolayer,where the adsorption of incident monochromatic linearly polarized light(hv=3.23 eV)along two planar directions with a nearly 100%optical selectivity can be achieved.Moreover,the spin–orbit coupling(SOC)induced spin splitting of valence band edges and out-of-plane textured spin configuration occur in ZrOI_(2) monolayer.In the meanwhile,the unidirectional spin–orbit field protected by C2v wave-vector point group can further create the persistent spin helix(PSH)state,leading to the extraordinarily long spin carrier lifetime.More importantly,the nonvolatile control of PSH state via the electric field induced polarization reversal has also been demonstrated for FE-ZrOI_(2) monolayer,which manifests as a great advantage for applications of ZrOI_(2) as the lowdimensional spin-field effect transistor and all-electric spintronics devices.