SPEX: A Generic Framework for Enhancing Neural Social Recommendation

Social Recommender Systems (SRS) have attracted considerable attention since its accompanying service, social networks, helps increase user satisfaction and provides auxiliary information to improve recommendations. However, most existing SRS focus on social influence and ignore another essential social phenomenon, i.e., social homophily. Social homophily, which is the premise of social influence, indicates that people tend to build social relations with similar people and form influence propagation paths. In this article, we propose a generic framework Social PathExplorer (SPEX) to enhance neural SRS. SPEX treats the neural recommendation model as a black box and improves the quality of recommendations by modeling the social recommendation task, the formation of social homophily, and their mutual effect in the manner of multi-task learning. We design a Graph Neural Network based component for influence propagation path prediction to help SPEX capture the rich information conveyed by the formation of social homophily. We further propose an uncertainty based task balancing method to set appropriate task weights for the recommendation task and the path prediction task during the joint optimization. Extensive experiments have validated that SPEX can be easily plugged into various state-of-the-art neural recommendation models and help improve their performance. The source code of our work is available at: https://github.com/XMUDM/SPEX.

Influence Maximization Algorithm Based on Reverse Reachable Set

Most of the existing influence maximization algorithms are not suitable for large-scale social networks due to their high time complexity or limited influence propagation range. Therefore, a D-RIS (dynamic-reverse reachable set) influence maximization algorithm is proposed based on the independent cascade model and combined with the reverse reachable set sampling. Under the premise that the influence propagation function satisfies monotonicity and submodularity, the D-RIS algorithm uses an automatic debugging method to determine the critical value of the number of reverse reachable sets, which not only obtains a better influence propagation range but also greatly reduces the time complexity. The experimental results on the two real datasets of Slashdot and Epinions show that D-RIS algorithm is close to the CELF (cost-effective lazy-forward) algorithm and higher than RIS algorithm, HighDegree algorithm, LIR algorithm, and pBmH (population-based metaheuristics) algorithm in influence propagation range. At the same time, it is significantly better than the CELF algorithm and RIS algorithm in running time, which indicates that D-RIS algorithm is more suitable for large-scale social network.

Exploring Intelligent Approach of Influence Minimization Considering the Node Surveillance in Online Social Networks

Attractive information such as innovations, awareness campaigns, branding, and advertising help people positively. Whereas, awful information such as rumors, malicious viruses, pornography, and revenge disturb people. The negative information contributes to chaos among people; therefore, it is to be blocked and hinder from further diffusion. This has motivated us towards the study of the problem named influence minimization. As the real world network can be modeled to a multilayer network, we focus our study towards the information diffusion through a multilayer network. Each node assigns a threshold, and its variation affects the rate of influence propagation across the network. In the influence minimization problem, the energy level of each node changes that help to formulate the function that minimizes the influence propagation. By applying two reduction policies, we are able to optimize our objective of minimizing the influence towards repulsive information. In this article, we consider the user response and its surveillance in the network. Repeated experiments on real networks has helped us to validate the proposed methods.

Influence Maximization Algorithm Based on Reverse Reachable Set

Most of the existing influence maximization algorithms are not suitable for large-scale social networks due to their high time complexity or limited influence propagation range. Therefore, a D-RIS influence maximization algorithm is proposed based on the independent cascade model and combined with the reverse reachable set sampling. Under the premise that the influence propagation function satisfies monotonicity and submodularity, the D-RIS algorithm uses automatic debugging method to determine the critical value of the number of reverse reachable sets, which not only obtains a better influence propagation range, and greatly reduce the time complexity. The experimental results on the two real data sets of Slashdot and Epinions show that D-RIS algorithm is close to the CELF algorithm and higher than RIS algorithm, HighDegree algorithm, LIR algorithm and pBmH algorithm in influence propagation range. At the same time, it is significantly better than the CELF algorithm and RIS algorithm in running time, which indicates that D-RIS algorithm is more suitable for large scale social network.

Cladode size and collection time for pitahaya propagation

ABSTRACT Cutting is a propagation method with the advantages of early production and uniform cultivation. Some factors influence propagation and rooting, such as the cutting size and the time of year the collection is performed. Thus, the present work aimed to evaluate the ideal size of white-fleshed red pitahaya cladodes and the time of their collection for crop propagation by cutting in view of the physiological quality of the produced clonal plants to enable more appropriate cultural management and increase the cultivation area. The experiment was conducted at the Faculty of Engineering (UNESP) using three cladode sizes (cuttings) with lengths of 10, 20 and 40 cm collected in two seasons (summer and winter). The experimental design used was completely randomized in a split-time scheme, with no dependence on the factors and 20 replicates. Evaluations of the biometric factors related to sprouts and cladode rooting were carried out 60 days after cutting. According to the results, there were significant differences among treatments, with a significant interaction of the number of sprouts. It can be concluded that, regarding the size of the cladodes, it is recommended, when possible, to use cladodes 40 cm in length; regarding the time of collection, it is recommended that collection be conducted in the winter period to favor the development of better-quality clonal plants.

Analisis Kejadian pada Sistem Pendingin Primer Reaktor Menggunakan Functional Modeling

Selama waktu operasi reaktor, struktur, sistem dan komponen (SSK) reaktor, misalnya sistem pendingin primer, akan mengalami penuaan atau keusangan yang akan mempengaruhi kinerja dan operasi selamat dari reaktor tersebut. Hal ini juga berlaku pada Reaktor Serba Guna G.A. Siwabessy (RSG-GAS) yang usianya lebih dari 30 tahun. Oleh karena itu program manajemen penuaan harus dilakukan untuk mengatasi hal tersebut. Salah satu aktivitas yang dilakukan adalah dengan melakukan penapisan komponen kritis sistem pendingin primer. Penelitian ini bertujuan untuk melakukan penapisan tersebut menggunakan model multilevel flow modeling (MFM) pada sistem pendingin primer RSG-GAS. MFM adalah salah satu metode functional modeling yang mengubah sistem kompleks menjadi struktur fungsi-fungsi yang saling terhubung dengan hubungan sebab akibat. Metode yang dilakukan adalan dengan menerapkan beberapa skenario kejadian kecelakaan loss of flow accident (LOFA) yang terdapat pada Laporan Analisis Keselamatan (LAK) RSG-GAS pada model MFM tersebut. Dampak dari kejadian tersebut dapat dianalisis menggunakan aturan jalur perambatan (influence propagation). Hasil investigasi berupa komponen-komponen yang terdampak, yaitu katup isolasi, pompa primer dan alat penukar panas, dikelompokkan sebagai komponen kritis dan harus mendapat perhatian untuk penanganan lebih lanjut. Jika komponen-komponen tersebut mengalami keusangan atau kerusakan maka harus dilakukan perawatan atau penggantian sehingga kinerja reaktor dapat dipertahankan dan reaktor dapat tetap beroperasi dengan aman dan selamat.