A photo-modulated nitric oxide delivering hydrogel for the accelerated healing of biofilm infected chronic wounds.

Biofilm infection and impaired healing of chronic wounds are posing tremendous challenges in clinical practice. In this study, we presented a versatile antimicrobial hydrogel capable of delivering nitric oxide (NO) in a controllable manner to dissipate biofilms, eliminate microorganisms, and promote the healing of chronic wounds. This hydrogel was constructed by Schiff-base crosslinking of oxidized dextran and antimicrobial peptide ε-poly-lysine, further encapsulating photothermal nanoparticles bearing NO donor. This hydrogel could continuously and slowly release NO, effectively dissipating biofilms, and promoting the proliferation of mouse fibroblasts and the migration of endothelial cells. Upon exposure to NIR laser irradiation, the hydrogel generated hyperthermia and rapidly released NO, resulting in the efficient elimination of a broad spectrum of drug-resistant Gram-positive/negative bacterial and fungal biofilms through the synergistic effects of NO, photothermal therapy, and the antibacterial peptide. Notably, the hydrogel demonstrated exceptional in vivo therapeutic outcomes in accelerating the healing process of mice diabetic wounds infected with methicillin-resistant Staphylococcus aureus by successfully eliminating biofilm infection, regulating inflammation, and facilitating angiogenesis and collagen deposition. Overall, this proposed hydrogel shows great promise in accommodating the various demands of the complex repair process of chronic wounds infected with biofilms. STATEMENT OF SIGNIFICANCE: : The presence of biofilm infections and underlying dysfunctions in the healing process made chronic wound become stuck in the inflammation stage and difficult to heal. This work developed a NIR laser-modulated three-stage NO-releasing versatile antimicrobial hydrogel (DEPN) exhibiting good therapeutic efficacy for chronic wound. This DEPN hydrogel could inherently and slowly released NO to disperse biofilm. Upon NIR laser irradiation, the DEPN hydrogel generated hyperthermia and induced a rapid burst release of NO effectively eliminating a broad spectrum of drug-resistant bacterial and fungal biofilms. Subsequently, the DEPN hydrogel continually release NO slowly to promote the tissue remolding. This DEPN hydrogel displays great potential in treatment of chronic wounds infected with biofilm.

Exploring refined dual visual features cross-combination for image captioning.

For current image caption tasks used to encode region features and grid features Transformer-based encoders have become commonplace, because of their multi-head self-attention mechanism, the encoder can better capture the relationship between different regions in the image and contextual information. However, stacking Transformer blocks necessitates quadratic computation through self-attention to visual features, not only resulting in the computation of numerous redundant features but also significantly increasing computational overhead. This paper presents a novel Distilled Cross-Combination Transformer (DCCT) network. Technically, we first introduce a distillation cascade fusion encoder (DCFE), where a probabilistic sparse self-attention layer is used to filter out some redundant and distracting features that affect attention focus, aiming to obtain more refined visual features and enhance encoding efficiency. Next, we develop a parallel cross-fusion attention module (PCFA) that fully exploits the complementarity and correlation between grid and region features to better fuse the encoded dual visual features. Extensive experiments conducted on the MSCOCO dataset demonstrate that our proposed DCCT method achieves outstanding performance, rivaling current state-of-the-art approaches.

Rolling up 2D WSe2 Nanosheets to 1D Anisotropic Nanoscrolls for Polarization-Sensitive Photodetectors.

The intrinsic low-symmetry crystal structures or external geometries of low-dimensional materials are crucial for polarization-sensitive photodetection. However, these inherently anisotropic materials are limited in variety, and their anisotropy is confined to specific crystal directions. Transforming 2D semiconductors, such as WSe2, from isotropic 2D nanosheets into anisotropic 1D nanoscrolls expands their application in polarization photodetection. Despite this considerable potential, research on polarization photodetection based on nanoscrolls remains scarce. Here, the uniform crystalline orientation of WSe2 nanoscrolls is achieved conveniently and efficiently by applying ethanol droplets to vapor deposition-grown bilayer WSe2 nanosheets. Angle-resolved polarized Raman spectroscopy of WSe2 nanoscrolls demonstrates vibrational anisotropy. Photodetectors based on these nanoscrolls show competitive overall performance with a broadband detection range from 405 to 808 nm, a competitive on/off ratio of ≈900, a high detectivity of 3.4 × 108 Jones, and a fast response speed of ≈30 ms. Additionally, WSe2 nanoscroll-based photodetectors exhibit strong polarization-sensitive detection with a maximum dichroic ratio of 1.5. More interestingly, due to high photosensitivity, the WSe2 nanoscroll detectors can easily record sequential puppy images. This work reveals the potential of WSe2 nanoscrolls as excellent polarization-sensitive photodetectors and provides new insights into the development of high-performance optoelectronic devices.

Synthesis, Modulation, and Application of Two-Dimensional TMD Heterostructures.

Two-dimensional (2D) transition metal dichalcogenide (TMD) heterostructures have attracted a lot of attention due to their rich material diversity and stack geometry, precise controllability of structure and properties, and potential practical applications. These heterostructures not only overcome the inherent limitations of individual materials but also enable the realization of new properties through appropriate combinations, establishing a platform to explore new physical and chemical properties at micro-nano-pico scales. In this review, we systematically summarize the latest research progress in the synthesis, modulation, and application of 2D TMD heterostructures. We first introduce the latest techniques for fabricating 2D TMD heterostructures, examining the rationale, mechanisms, advantages, and disadvantages of each strategy. Furthermore, we emphasize the importance of characteristic modulation in 2D TMD heterostructures and discuss some approaches to achieve novel functionalities. Then, we summarize the representative applications of 2D TMD heterostructures. Finally, we highlight the challenges and future perspectives in the synthesis and device fabrication of 2D TMD heterostructures and provide some feasible solutions.

Mining core information by evaluating semantic importance for unpaired image captioning.

Recently, exciting progress has been made in the research of supervised image captioning. However, manually annotated image-annotation pair data is difficult and expensive to obtain. Therefore, unpaired image captioning becomes an emerging challenge. This paper proposes a method called Mining Core Information by Evaluating Semantic Importance (MCIESI) for Unpaired Image Captioning, which is a method for image captioning using unpaired images and sentences. The main difference from the existing methods is that MCIESI focuses on mining the information that should be described in the image and embodies them in the generated natural language that conforms to human thinking. To achieve this goal, we use scene graphs to represent the semantics of images and evaluates the importance of objects and interaction relationships to mine core information in images, which are then encouraged to be embodied in generated sentences through semantic constraint. Combined with grammatical constraint using adversarial training with real sentence corpus and relative constraint using a triplet loss, the generator is trained to generate semantically plausible and grammatically correct sentences. Extensive experiments verify the effectiveness of MCIESI.

Band alignment engineering of 2D/3D halide perovskite lateral heterostructures.

Two-dimensional (2D)/three-dimensional (3D) halide perovskite heterostructures have been extensively studied for their ability to combine the outstanding long-term stability of 2D perovskites with the superb optoelectronic properties of 3D perovskites. While current studies mostly focus on vertically stacked 2D/3D perovskite heterostructures, a theoretical understanding regarding the optoelectronic properties of 2D/3D perovskite lateral heterostructures is still lacking. Herein, we construct a series of 2D/3D perovskite lateral heterostructures to study their optoelectronic properties and interfacial charge transfer using density functional theory (DFT) calculations. We find that the band alignments of 2D/3D heterostructures can be regulated by varying the quantum-well thickness of 2D perovskites. Moreover, decreasing the 2D component ratio in 2D/3D heterostructures can be favorable to form type-I band alignment, whereas a large component ratio of 2D perovskites tends to form type-II band alignment. We can improve the amount of charge transfer at the 2D/3D perovskite interfaces and the light absorption of 2D perovskites by increasing quantum-well thickness. These present findings can provide a clear designing principle for achieving 3D/2D perovskite lateral heterostructures with tunable optoelectronic properties.

Visible-Light-Driven Z-Type Pg-C3N4/Nitrogen Doped Biochar/BiVO4 Photo-Catalysts for the Degradation of Norfloxacin.

Antibiotics cannot be effectively removed by traditional wastewater treatment processes, and have become widespread pollutants in various environments. In this study, a Z-type heterojunction photo-catalyst Pg-C3N4 (PCN)/Nitrogen doped biochar (N-Biochar)/BiVO4 (NCBN) for the degradation of norfloxacin (NOR) was prepared by the hydrothermal method. The specific surface area of the NCBN (42.88 m2/g) was further improved compared to BiVO4 (4.528 m2/g). The photo-catalytic performance of the catalyst was investigated, and the N-Biochar acted as a charge transfer channel to promote carrier separation and form Z-type heterojunctions. Moreover, the NCBN exhibited excellent performance (92.5%) in removing NOR, which maintained 70% degradation after four cycles. The main active substance of the NCBN was •O2-, and the possible degradation pathways are provided. This work will provide a theoretical basis for the construction of heterojunction photo-catalysts.

Active multi-focus vortex beam terahertz encoding metasurface based on Dirac semimetals.

An electromagnetic wavefront can be flexibly manipulated by discrete phase coding on the coding unit. In this paper, we designed two coding metasurfaces with 1-bit and 3-bit based on active tuning of Dirac semimetals by controlling the Fermi level (E F) with an external polarization voltage. The size and structure of the metasurface remain unchanged with this strategy. Both designs were found to be dynamically tunable. The 1-bit coding metasurface enables beam conversion, single-focus switching, and switching between single-focus and multi-focus. On the other hand, the 3-bit coding metasurface enables the switching between vortex beams and single-beam mirror reflections. These proposed structures have potential applications in terahertz (THz) communications and terahertz-focused imaging, opening up new possibilities for the dynamic modulation of THz waves.

Vapor Phase Growth of Air-Stable Hybrid Perovskite FAPbBr3 Single-Crystalline Nanosheets.

Organic-inorganic hybrid perovskites have attracted tremendous attention owing to their fascinating optoelectronic properties. However, their poor air stability seriously hinders practical applications, which becomes more serious with thickness down to the nanoscale. Here we report a one-step vapor phase growth of HC(NH2)2PbBr3 (FAPbBr3) single-crystalline nanosheets of tunable size up to 50 µm and thickness down to 20 nm. The FAPbBr3 nanosheets demonstrate high stability for over months of exposure to air with no degradation in surface roughness and photoluminescence efficiency. Besides, the FAPbBr3 photodetectors exhibit superior overall performance as compared to previous devices based on nonlayered perovskite nanosheets, such as an ultralow dark current of 24 pA, an ultrahigh responsivity of 1033 A/W, an external quantum efficiency over 3000%, a rapid response time around 25 ms, and a high on/off ratio of 104. This work provides a strategy to tackle the challenges of hybrid perovskites toward integrated optoelectronics with requirements of nanoscale thickness, high stability, and excellent performance.

Effects of brain-Computer interface combined with mindfulness therapy on rehabilitation of hemiplegic patients with stroke: a randomized controlled trial.

Aim: To explore the effects of brain-computer interface training combined with mindfulness therapy on Hemiplegic Patients with Stroke. Background: The prevention and treatment of stroke still faces great challenges. Maximizing the improvement of patients' ability to perform activities of daily living, limb motor function, and reducing anxiety, depression, and other social and psychological problems to improve patients' overall quality of life is the focus and difficulty of clinical rehabilitation work. Methods: Patients were recruited from December 2021 to November 2022, and assigned to either the intervention or control group following a simple randomization procedure (computer-generated random numbers). Both groups received conventional rehabilitation treatment, while patients in the intervention group additionally received brain-computer interface training and mindfulness therapy. The continuous treatment duration was 5 days per week for 8 weeks. Limb motor function, activities of daily living, mindfulness attention awareness level, sleep quality, and quality of life of the patients were measured (in T0, T1, and T2). Generalized estimated equation (GEE) were used to evaluate the effects. The trial was registered with the Chinese Clinical Trial Registry (ChiCTR2300070382). Results: A total of 128 participants were randomized and 64 each were assigned to the intervention and control groups (of these, eight patients were lost to follow-up). At 6 months, compared with the control group, intervention group showed statistically significant improvements in limb motor function, mindful attention awareness, activities of daily living, sleep quality, and quality of life. Conclusion: Brain-computer interface combined with mindfulness therapy training can improve limb motor function, activities of daily living, mindful attention awareness, sleep quality, and quality of life in hemiplegic patients with stroke. Impact: This study provides valuable insights into post-stroke care. It may help improve the effect of rehabilitation nursing to improve the comprehensive ability and quality of life of patients after stroke. Clinical review registration: https://www.chictr.org.cn/, identifier ChiCTR2300070382.

Study on semi-bionic extraction of Astragalus polysaccharide and its anti-aging activity in vivo.

Astragalus membranaceus (A. membranaceus) is a homologous plant with high medicinal and edible value. Therefore, the extraction methods of Astragalus polysaccharide (APS) have attracted the attention of many research groups, but the yield of the active components is still not high. The aim of this study was to extract APS by a semi-bionic extraction method, optimize the extraction process, and evaluate the anti-aging activities of APS in vivo. The results showed that the APS yield was 18.23% when extracted by the semi-bionic extraction method. Anti-aging evaluation in rats showed that APS extracted by this method significantly decreased the malondialdehyde (MDA) content and increased superoxide dismutase (SOD) activity to cope with D-galactose-induced aging. Serum metabolomic analysis indicated that a total of 48 potential biomarkers showed significant differences, mainly involving 5 metabolic pathways. These altered metabolic pathways were mainly related to energy metabolism, amino acid metabolism, and lipid metabolism. These results indicated that the semi-bionic extraction method can effectively improve the yield of APS, and the extracted APS exhibited anti-aging activity in rats. Our study provided a novel and effective method to extract APS and indicated that APS can be used as functional food and natural medicine to delay aging and prevent its complications.

A novel frequency-dependent lattice Boltzmann model with a single force term for electromagnetic wave propagation in dispersive media.

Electromagnetic wave simulation is of pivotal importance in the design and implementation of photonic nano-structures. In this study, we developed a lattice Boltzmann model with a single extended force term (LBM-SEF) to simulate the propagation of electromagnetic waves in dispersive media. By reconstructing the solution of the macroscopic Maxwell equations using the lattice Boltzmann equation, the final form only involves an equilibrium term and a non-equilibrium force term. The two terms are evaluated using the macroscopic electromagnetic variables and the dispersive effect, respectively. The LBM-SEF scheme is capable of directly tracking the evolution of macroscopic electromagnetic variables, leading to lower virtual memory requirement and facilitating the implementation of physical boundary conditions. The mathematical consistency of the LBM-SEF with the Maxwell equations was validated by using the Champman-Enskog expansion; while three practical models were used to benchmark the numerical accuracy, stability, and flexibility of the proposed method.

Switchable optical vortex beam generator based on an all-dielectric metasurface governed by merging bound states in the continuum.

The polarization topology around the bound states in continuum (BIC) affects the optical vortex (OV) beam generation. We propose a cross-cross-shaped resonator based on a THz metasurface to realize an OV beam generator in real space by exploiting the inherent winding topology around the BIC. The BIC merging at the point Γ is achieved by tuning the width of the cross resonator, which significantly improves the Q factor and enhances the field localization. Furthermore, the switching between the high-order OV beam generator governed by the merged BIC and the low-order OV beam generator is realized. This extends the application of BIC in modulating orbital angular momentum.

Similarity measures-based graph co-contrastive learning for drug-disease association prediction.

MOTIVATION: An imperative step in drug discovery is the prediction of drug-disease associations (DDAs), which tries to uncover potential therapeutic possibilities for already validated drugs. It is costly and time-consuming to predict DDAs using wet experiments. Graph Neural Networks as an emerging technique have shown superior capacity of dealing with DDA prediction. However, existing Graph Neural Networks-based DDA prediction methods suffer from sparse supervised signals. As graph contrastive learning has shined in mitigating sparse supervised signals, we seek to leverage graph contrastive learning to enhance the prediction of DDAs. Unfortunately, most conventional graph contrastive learning-based models corrupt the raw data graph to augment data, which are unsuitable for DDA prediction. Meanwhile, these methods could not model the interactions between nodes effectively, thereby reducing the accuracy of association predictions. RESULTS: A model is proposed to tap potential drug candidates for diseases, which is called Similarity Measures-based Graph Co-contrastive Learning (SMGCL). For learning embeddings from complicated network topologies, SMGCL includes three essential processes: (i) constructs three views based on similarities between drugs and diseases and DDA information; (ii) two graph encoders are performed over the three views, so as to model both local and global topologies simultaneously; and (iii) a graph co-contrastive learning method is introduced, which co-trains the representations of nodes to maximize the agreement between them, thus generating high-quality prediction results. Contrastive learning serves as an auxiliary task for improving DDA predictions. Evaluated by cross-validations, SMGCL achieves pleasing comprehensive performances. Further proof of the SMGCL's practicality is provided by case study of Alzheimer's disease. AVAILABILITY AND IMPLEMENTATION: https://github.com/Jcmorz/SMGCL.

First principles terahertz spectroscopy of molecular crystals: the crucial role of periodic boundary conditions benchmarked with experimental L-ascorbic acid spectra.

The terahertz (THz) region vibration spectral signatures of molecular crystals can usually be ascribed to the low-frequency vibrational modes related to weak intermolecular interactions, e.g. van der Waals (vdW) interactions or hydrogen bonding. These interactions collectively dictate the compositional units deviating from their equilibrium configurations. The collective movements are intrinsically long-range, and hence the boundary conditions used for theoretical calculation can affect the corresponding potential energy gradients and alter the vibrational features. In this work, we constructed a series of finite-sized cluster models with varying sizes and an extended periodic crystal model for L-ascorbic acid (L-AA) crystals. Density functionals with both semi-local contributions and nonlocal vdW terms, implemented with either atom-centered Gaussian basis or plane waves, were tested. By comparing first principles calculations with experimental time-domain spectra (TDS), we found that the non-local vdW functional opt-B88 combined with a periodic boundary condition is capable of assigning all the experimental features in the 0.2-1.6 THz region. Calculations with cluster models failed in this task. Even worse, the deficiency of the cluster models varied with cluster sizes, and did not converge as the cluster size grew. Our results demonstrate that an appropriate periodic boundary condition is essential to correctly assign and analyze the THz vibration spectra of molecular crystals.

Surface charge adaptive nitric oxide nanogenerator for enhanced photothermal eradication of drug-resistant biofilm infections.

Due to protection of extracellular polymeric substances, the therapeutic efficiency of conventional antimicrobial agents is often impeded by their poor infiltration and accumulation in biofilm. Herein, one type of surface charge adaptable nitric oxide (NO) nanogenerator was developed for biofilm permeation, retention and eradication. This nanogenerator (PDG@Au-NO/PBAM) is composed of a core-shell structure: thermo-sensitive NO donor conjugated AuNPs on cationic poly(dopamine-co-glucosamine) nanoparticle (PDG@Au-NO) served as core, and anionic phenylboronic acid-acryloylmorpholine (PBAM) copolymer was employed as a shell. The NO nanogenerator featured long circulation and good biocompatibility. Once the nanogenerator reached acidic biofilm, its surface charge would be switched to positive after shell dissociation and cationic core exposure, which was conducive for the nanogenerator to infiltrate and accumulate in the depth of biofilm. In addition, the nanogenerator could sustainably generate NO to disturb the integrity of biofilm at physiological temperature, then generate hyperthermia and explosive NO release upon NIR irradiation to efficiently eradicate drug-resistant bacteria biofilm. Such rational design offers a promising approach for developing nanosystems against biofilm-associated infections.

Removal behaviors and mechanism of polystyrene microplastics by coagulation/ultrafiltration process: Co-effects of humic acid.

Microplastics (MPs) have been detected in drinking water, which could absorb or accumulate humic acid (HA) and threaten the water quality. Coagulation-ultrafiltration (CUF) is a common drinking water treatment technology, but its behavior and mechanism of removing MPs and MPs-HA remain unclear. In this study, the removal mechanism of polystyrene (PS)-MPs coagulated by Al- and Fe-based salts with or without HA was investigated to optimize the CUF process. The results showed that Al-based salt (92.7 %) was better than Fe-based salt (91.2 %) in the removal efficiency of PS or HA, and the optimal coagulants dosage of PS-HA composite system (12 mg·L-1) was higher than that of the individual PS system (9 mg·L-1). Moreover, the coagulation mechanism was studied by Fourier transform infrared spectroscope (FTIR) and X-ray photoelectron spectroscopy (XPS). The oxygen group in PS and PS-HA was the main binding site of Al and Fe hydrolysate, and the effects of charge neutralization, adsorption bridging, and sweep flocculation became weaker in turn at the optimal dosage. In addition, the cake layer formed by coagulation and the presence of HA alleviated the irreversible membrane fouling by intercepting flow and re-adsorption. This study guides the improvement of the traditional drinking water treatment process to remove MPs.

Thickness-dependent excitonic properties of WSe2/FePS3 van der Waals heterostructures.

van der Waals heterostructures (vdWHs), with their flexible combination of various two-dimensional (2D) materials, are continuously revealing new physics and functionalities. 2D magnetic materials have recently become a focus due to their fascinating electronic and spintronic properties. However, there has rarely been any investigation of the optical properties of 2D magnetic materials-based heterostructures. Herein, we construct a new WSe2/FePS3 heterostructure, in which WSe2 works as a "sensor" to visualize the thickness-dependent properties of FePS3. As characterized by photoluminescence (PL) spectra, whether under or on top of the FePS3, the PL intensity of the monolayer WSe2 is strongly quenched. The quenching effect becomes more obvious as the FePS3 thickness increases. This is because of the efficient charge transfer process occurring at the WSe2/FePS3 interface with type II band alignment, which is faster for thicker FePS3, as is evident from transient absorption measurements. The thickness-dependent charge transfer process and corresponding excitonic properties are further revealed in low-temperature photoluminescence spectra of WSe2/FePS3 heterostructures. Our results show that the thickness of 2D magnetic materials can work as an experimental tuning knob to manipulate the optical performance of conventional 2D semiconductors, endowing van der Waals heterostructures with more unexpected properties and functionalities.

Controlled Synthesis of Sub-Millimeter Nonlayered WO2 Nanoplates via a WSe2 -Assisted Method.

2D metal oxides (2DMOs) have stimulated tremendous attention due to their distinct electronic structures and abundant surface chemistry. However, it remains a standing challenge for the synthesis of 2DMOs because of their intrinsic 3D lattice structure and ultrahigh synthesis temperature. Here, a reliable WSe2 -assisted chemical vapor deposition (CVD) strategy to grow nonlayered WO2 nanoplates with tunable thickness and lateral dimension is reported. Optical microscopy and scanning electron microscopy studies demonstrate that the WO2 nanoplates exhibit a well-faceted rhombic geometry with a lateral dimension up to the sub-millimeter level (≈135 µm), which is the largest size of 2DMO single crystals obtained by CVD to date. Scanning transmission electron microscopy studies reveal that the nanoplates are high-quality single crystals. Electrical measurements show the nanoplates exhibit metallic behavior with strong anisotropic resistance, outstanding conductivity of 1.1 × 106  S m-1 , and breakdown current density of 7.1 × 107  A cm-2 . More interestingly, low-temperature magnetotransport studies demonstrate that the nanoplates show a quantum-interference-induced weak-localization effect. The developed WSe2 -assisted strategy for the growth of WO2 nanoplates can enrich the library of 2DMO materials and provide a material platform for other property explorations based on 2D WO2 .

FIRE: knowledge-enhanced recommendation with feature interaction and intent-aware attention networks.

To solve the information overload issue and enhance the user experience of various web applications, recommender systems aim to better model user interests and preferences. Knowledge Graphs (KGs), consisting of real-world objective facts and fruitful entities, play a vital role in recommender systems. Recently, a technological trend has been to develop end-to-end Graph Neural Networks (GNNs)-based knowledge-aware recommendation (a.k.a., Knowledge Graph Recommendation, KGR) models. Unfortunately, current GNNs-based KGR approaches focus on how to capture high-order feature information on KGs while neglecting the following two crucial limitations: 1) The explicitly high-order feature interaction and fusion mechanism and 2) The valid user intent modelling mechanism. As such, these issues lead to insufficient user/item representation learning capability and unsatisfactory KGR performance. In this work, we present a novel Knowledge-enhanced Re commendation with F eature I nteraction and Intent-aware Attention Networks (FIRE) to address the latent intent modelling and high-order feature interaction deficiencies ignored by existing KGR methods. Based on the prototype user/item representation learning leveraging the GNNs-based approach, our model offers the following major improvements: One is the innovative use of Convolutional Neural Networks (CNNs) that perform vertical convolutional (a.k.a., bit-level convolutional) and horizontal convolutional (a.k.a., vector-level convolutional) processes to model multi-granular high-order feature interactions to enhance item-side representation learning. Another is to model users' latent intent factors by utilizing a two-level attention mechanism (i.e., node- and intent-level attention mechanism) to enhance user-side representation learning. Extensive experiments on three KGs domain public datasets demonstrate that our method outperforms the existing state-of-the-art baseline. Last but not least, numerous ablation- and model studies demystify the working mechanism and elucidate the plausibility of the proposed model.