HyperSoRec: Exploiting Hyperbolic User and Item Representations with Multiple Aspects for Social-aware Recommendation

Social recommendation has achieved great success in many domains including e-commerce and location-based social networks. Existing methods usually explore the user-item interactions or user-user connections to predict users’ preference behaviors. However, they usually learn both user and item representations in Euclidean space, which has large limitations for exploring the latent hierarchical property in the data. In this article, we study a novel problem of hyperbolic social recommendation, where we aim to learn the compact but strong representations for both users and items. Meanwhile, this work also addresses two critical domain-issues, which are under-explored. First, users often make trade-offs with multiple underlying aspect factors to make decisions during their interactions with items. Second, users generally build connections with others in terms of different aspects, which produces different influences with aspects in social network. To this end, we propose a novel graph neural network (GNN) framework with multiple aspect learning, namely, HyperSoRec. Specifically, we first embed all users, items, and aspects into hyperbolic space with superior representations to ensure their hierarchical properties. Then, we adapt a GNN with novel multi-aspect message-passing-receiving mechanism to capture different influences among users. Next, to characterize the multi-aspect interactions of users on items, we propose an adaptive hyperbolic metric learning method by introducing learnable interactive relations among different aspects. Finally, we utilize the hyperbolic translational distance to measure the plausibility in each user-item pair for recommendation. Experimental results on two public datasets clearly demonstrate that our HyperSoRec not only achieves significant improvement for recommendation performance but also shows better representation ability in hyperbolic space with strong robustness and reliability.

Persian Fake News Detection: Neural Representation and Classification at Word and Text Levels

Nowadays, broadcasting news on social media and websites has grown at a swifter pace, which has had negative impacts on both the general public and governments; hence, this has urged us to build a fake news detection system. Contextualized word embeddings have achieved great success in recent years due to their power to embed both syntactic and semantic features of textual contents. In this article, we aim to address the problem of the lack of fake news datasets in Persian by introducing a new dataset crawled from different news agencies, and propose two deep models based on the Bidirectional Encoder Representations from Transformers model (BERT), which is a deep contextualized pre-trained model for extracting valuable features. In our proposed models, we benefit from two different settings of BERT, namely pool-based representation, which provides a representation for the whole document, and sequence representation, which provides a representation for each token of the document. In the former one, we connect a Single Layer Perceptron (SLP) to the BERT to use the embedding directly for detecting fake news. The latter one uses Convolutional Neural Network (CNN) after the BERT’s embedding layer to extract extra features based on the collocation of words in a corpus. Furthermore, we present the TAJ dataset, which is a new Persian fake news dataset crawled from news agencies’ websites. We evaluate our proposed models on the newly provided TAJ dataset as well as the two different Persian rumor datasets as baselines. The results indicate the effectiveness of using deep contextualized embedding approaches for the fake news detection task. We also show that both BERT-SLP and BERT-CNN models achieve superior performance to the previous baselines and traditional machine learning models, with 15.58% and 17.1% improvement compared to the reported results by Zamani et al. [ 30 ], and 11.29% and 11.18% improvement compared to the reported results by Jahanbakhsh-Nagadeh et al. [ 9 ].

A mixed multiscale FEM for the eddy current problem with T,Φ-Φ and vector hysteresis

Purpose This work introduces an efficient and accurate technique to solve the eddy current problem in laminated iron cores considering vector hysteresis. Design/methodology/approach The mixed multiscale finite element method based on the based on the T,Φ-Φ formulation, with the current vector potential T and the magnetic scalar potential Φ allows the laminated core to be modelled as a single homogeneous block. This means that the individual sheets do not have to be resolved, which saves a lot of computing time and reduces the demands on the computer system enormously. Findings As a representative numerical example, a single-phase transformer with 4, 20 and 184 sheets is simulated with great success. The eddy current losses of the simulation using the standard finite element method and the simulation using the mixed multiscale finite element method agree very well and the required simulation time is tremendously reduced. Originality/value The vector Preisach model is used to account for vector hysteresis and is integrated into the mixed multiscale finite element method for the first time.

Anodic Alumina Membranes: From Electrochemical Growth to Use as Template for Fabrication of Nanostructured Electrodes

The great success of anodic alumina membranes is due to their morphological features coupled to both thermal and chemical stability. The electrochemical fabrication allows accurate control of the porous structure: in fact, the membrane morphological characteristics (pore length, pore diameter and cell density) can be controlled by adjusting the anodizing parameters (bath, temperature, voltage and time). This article deals with both the fabrication and use of anodic alumina membranes. In particular, we will show the specific role of the addition of aluminum ions to phosphoric acid-based anodizing solution in modifying the morphology of anodic alumina membranes. Anodic alumina membranes were obtained at −1 °C in aqueous solutions of 0.4 M H3PO4 added with different amounts of Al(OH)3. For sake of completeness, the formation of PAA in pure 0.4 M H3PO4 in otherwise identical conditions was also investigated. We found that the presence of Al(OH)3 in solution highly affects the morphology of the porous layer. In particular, at high Al(OH)3 concentration (close to saturation) more compact porous layers were formed with narrow pores separated by thick oxide. The increase in the electric charge from 20 to 160 C cm−2 also contributes to modifying the morphology of porous oxide. The obtained anodic alumina membranes were used as a template to fabricate a regular array of PdCo alloy nanowires that is a valid alternative to Pt for hydrogen evolution reaction. The PdCo alloy was obtained by electrodeposition and we found that the composition of the nanowires depends on the concentration of two metals in the deposition solution.

Ikonographische Strategien Claudians

This article focuses on the particular ways in which Claudian portrays the epic hunting episode in his Stil. 3. In addition to the poetic models that he re-elaborates, he takes up an iconographic language with which his public, the Roman élite, was very well acquainted: it is the same iconography that can be observed in the hunting mosaics of Dermech and Hippona—and above all in the Grande Caccia of Piazza Armerina. In both Claud. Stil. 3 and the mosaics, we encounter a hunt, or rather a collection of animals which takes place mainly in North Africa in preparation for the games in the Roman harena. Both the hunting episode in Claudian’s poem and the scenes of hunting in the mosaics point to the liberalitas or economical-political power, or even virtus, which the owners of the villas, or Stilicho himself, claimed for themselves. This clearly builds on a ‘language’ that the contemporary élite (4th century CE) appreciated and that Claudian exploited with great success.

Neural Network Potentials: A Concise Overview of Methods

In the past two decades, machine learning potentials (MLPs) have reached a level of maturity that now enables applications to large-scale atomistic simulations of a wide range of systems in chemistry, physics, and materials science. Different machine learning algorithms have been used with great success in the construction of these MLPs. In this review, we discuss an important group of MLPs relying on artificial neural networks to establish a mapping from the atomic structure to the potential energy. In spite of this common feature, there are important conceptual differences among MLPs, which concern the dimensionality of the systems, the inclusion of long-range electrostatic interactions, global phenomena like nonlocal charge transfer, and the type of descriptor used to represent the atomic structure, which can be either predefined or learnable. A concise overview is given along with a discussion of the open challenges in the field. Expected final online publication date for the Annual Review of Physical Chemistry, Volume 73 is April 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Prediction of lncRNA–Disease Associations via Closest Node Weight Graphs of the Spatial Neighborhood Based on the Edge Attention Graph Convolutional Network

Accumulated evidence of biological clinical trials has shown that long non-coding RNAs (lncRNAs) are closely related to the occurrence and development of various complex human diseases. Research works on lncRNA–disease relations will benefit to further understand the pathogenesis of human complex diseases at the molecular level, but only a small proportion of lncRNA–disease associations has been confirmed. Considering the high cost of biological experiments, exploring potential lncRNA–disease associations with computational approaches has become very urgent. In this study, a model based on closest node weight graph of the spatial neighborhood (CNWGSN) and edge attention graph convolutional network (EAGCN), LDA-EAGCN, was developed to uncover potential lncRNA–disease associations by integrating disease semantic similarity, lncRNA functional similarity, and known lncRNA–disease associations. Inspired by the great success of the EAGCN method on the chemical molecule property recognition problem, the prediction of lncRNA–disease associations could be regarded as a component recognition problem of lncRNA–disease characteristic graphs. The CNWGSN features of lncRNA–disease associations combined with known lncRNA–disease associations were introduced to train EAGCN, and correlation scores of input data were predicted with EAGCN for judging whether the input lncRNAs would be associated with the input diseases. LDA-EAGCN achieved a reliable AUC value of 0.9853 in the ten-fold cross-over experiments, which was the highest among five state-of-the-art models. Furthermore, case studies of renal cancer, laryngeal carcinoma, and liver cancer were implemented, and most of the top-ranking lncRNA–disease associations have been proven by recently published experimental literature works. It can be seen that LDA-EAGCN is an effective model for predicting potential lncRNA–disease associations. Its source code and experimental data are available at https://github.com/HGDKMF/LDA-EAGCN.

A semiotic analysis of multiple systems of logic: using tagmemic theory to assess the usefulness and limitations of formal logics, and to produce a mathematical lattice model including multiple systems of logic

Tagmemic theory as a semiotic theory can be used to analyze multiple systems of logic and to assess their strengths and weaknesses. This analysis constitutes an application of semiotics and also a contribution to understanding of the nature of logic within the context of human meaning. Each system of logic is best adapted to represent one portion of human rationality. Acknowledging this correlation between systems and their targets helps explain the usefulness of more than one system. Among these systems, the two-valued system of classical logic takes its place. All the systems of logic can be incorporated into a complex mathematical model that has a place for each system and that represents a larger whole in human reasoning. The model can represent why tight formal systems of logic can be applied in some contexts with great success, but in other contexts are not directly applicable. The result suggests that human reasoning is innately richer than any one formal system of logic.

Collaborative spinal robot system for laminectomy: a preliminary study

OBJECTIVE The application of robots in the field of pedicle screw placement has achieved great success. However, decompressive laminectomy, a step that is just as critical as pedicle screw placement, does not have a mature robot-assisted system. To address this lack, the authors designed a collaborative spine robot system to assist with laminectomy. In this study, they aimed to investigate the reliability of this novel collaborative spinal robot system and compare it with manual laminectomy (ML). METHODS Thirty in vitro porcine lumbar vertebral specimens were obtained as experimental bone specimens. Robot-assisted laminectomy (RAL) was performed on the left side of the lamina (n = 30) and ML was performed on the right side (n = 30). The time required for laminectomy on one side, whether the lamina was penetrated, and the remaining thickness of the lamina were compared between the two groups. RESULTS The time required for laminectomy on one side was longer in the RAL group than in the ML group (median 326 seconds [IQR 133 seconds] vs 108.5 seconds [IQR 43 seconds], p < 0.001). In the RAL group, complete lamina penetration occurred twice (6.7%), while in the ML group, it occurred 9 times (30%); the difference was statistically significant (p = 0.045). There was no statistically significant difference in the remaining lamina thickness between the two groups (median 1.035 mm [IQR 0.419 mm] vs 1.084 mm [IQR 0.383 mm], p = 0.842). CONCLUSIONS The results of this study confirm the safety of this novel spinal robot system for laminectomy. However, its efficiency requires further improvement.

Understanding the Molecular Mechanisms of Differences in Efficiency and Stability of All-polymer Solar Cells

In spite of the great success of all-polymer solar cells (all-PSCs) in terms of device efficiency mainly owing to the vigorous development of polymer donors (PDs) and polymer acceptors (PAs),...