Search

Sequential Recommendation (SR) methods play a crucial role in recommender systems, which aims to capture users’ dynamic interest from their historical interactions. Recently, Contrastive Learning (CL), which has emerged as a successful method for sequential recommendation, utilizes various data augmentations to generate contrastive views to mine supervised signals from data to alleviate data sparsity issues. However, most existing sequential data augmentation methods may destroy semantic sequential interaction characteristics. Meanwhile, they often adopt random operations when generating contrastive views leading to suboptimal performance. To this end, in this paper, we propose a Learnable Model Augmentation Contrastive learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes the model-based augmentation method to generate constructive views. Then, LMA4Rec uses Learnable Bernoulli Dropout (LBD) to implement learnable model augmentation operations. Next, contrastive learning is used between the contrastive views to extract supervised signals. Furthermore, a novel multi-positive contrastive learning loss alleviates the supervised sparsity issue. Finally, experiments on public datasets show that our LMA4Rec method effectively improved sequential recommendation performance compared with the state-of-the-art baseline methods.

Eco-friendly halide double perovskites are attracting significant attention as potential substitutes for traditional lead-based halide perovskites. However, their typically wide or indirect band gap limits further technological advancement. This study presents a new, eco-friendly, all-inorganic millimeter-scale CsCuAgI3single crystal (SC). The crystal exhibits a direct band gap of 2.02 eV at the G-point, markedly superior to that of traditional double perovskites. The absorption and photoluminescence spectra further corroborate its band gap attributes. Owing to the B-site Cu–Ag disorder, the crystal possesses a higher Urbach energy (119 meV), indicative of structural disorder. CsCuAgI3exhibits a wide Stokes shift of 230 nm, a wide full width at half-maximum (fwhm) of 152 nm, a long fluorescence lifetime of 7.29 μs, and excellent stability. In addition, a photoelectric detection prototype was prepared using a CsCuAgI3single crystal. Using a 375 nm laser as the excitation source, the device showed a very sensitive photoelectric response, clocking in at (0.37/0.21) seconds. This work offers new insights into developing novel lead-free double perovskite single crystals and exploring their potential applications.

After replacement of Pb2+by monovalent cations and trivalent cations in traditional double perovskites, the cubic unit cell formed in the crystal structure restricts the interaction between adjacent cation orbitals. Herein, we first design and synthesized a new-type lead-free double perovskite Cs3CuAgI5single crystal (SC) by antisolvent method. The Cs3CuAgI5single crystal exhibits direct band gap at the G point with a band gap of 2.63 eV and the differential charge density display structure is 0D. Furthermore, the Cs3CuAgI5perovskite exhibited an emission peak of 460 nm, a Stokes-Shift of 160 nm, a long fluorescence lifetime of 8.15 μs, and superior stability of photoluminescence (PL) intensity maintained at about 90% after 90 days and demonstrated excellent thermal stability. Additionally, a white-light emitting device was produced using the Cs3CuAgI5single crystal, showcasing outstanding white-light emission with a high color rendering index (CRI) of 87.5, a correlated color temperature (CCT) of 4879 K, and remarkable stability, even at elevated temperatures of up to 100 °C.

Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types of objects and different types of links. In real-world scenarios, new semantic relations constantly emerge and they typically appear with only a few labeled data. Since a variety of semantic relations exist in multiple heterogeneous graphs, the transferable knowledge can be mined from some existing semantic relations to help predict the new semantic relations with few labeled data. This inspires a novel problem of few-shot semantic relation prediction across heterogeneous graphs. However, the existing methods cannot solve this problem because they not only require a large number of labeled samples as input, but also focus on a single graph with a fixed heterogeneity. Targeting this novel and challenging problem, in this paper, we propose a Meta-learning based Graph neural network for Semantic relation prediction, named MetaGS. First, MetaGS decomposes the graph structure between objects into multiple normalized subgraphs, then adopts a two-view graph neural network to capture local heterogeneous information and global structure information of these subgraphs. Second, MetaGS aggregates the information of these subgraphs with a hyper-prototypical network, which can learn from existing semantic relations and adapt to new semantic relations. Third, using the well-initialized two-view graph neural network and hyper-prototypical network, MetaGS can effectively learn new semantic relations from different graphs while overcoming the limitation of few labeled data. Extensive experiments on three real-world datasets have demonstrated the superior performance of MetaGS over the state-of-the-art methods.

Sequential recommendation, which aims to recommend next item that the user will likely interact in a near future, has become essential in various Internet applications. Existing methods usually consider the transition patterns between items, but ignore the transition patterns between features of items. We argue that only the item-level sequences cannot reveal the full sequential patterns, while explicit and implicit feature-level sequences can help extract the full sequential patterns. Meanwhile, the item-level sequential recommendation also suffers from limited supervised signal issues. In this article, we propose a novel model Feature-level Deeper Self-Attention Network with Contrastive Learning (FDSA-CL) for sequential recommendation. Specifically, FDSA-CL first integrates various heterogeneous features of items into feature-level sequences with different weights through a vanilla attention mechanism. After that, FDSA-CL applies separated self-attention blocks on item-level sequences and feature-level sequences, respectively, to model item transition patterns and feature transition patterns. Moreover, we propose contrastive learning and item feature recommendation tasks to capture the embedding commonality and further utilize the beneficial interaction among the two levels, so as to alleviate the sparsity of the supervised signal and extract the most critical information. Finally, we jointly optimize the above tasks. We evaluate the proposed model using two real-world datasets and experimental results show that our model significantly outperforms the state-of-the-art approaches.

Graph Pattern based Node Matching (GPNM) is to find all the matches of the nodes in a data graph $G_D$GD based on a given pattern graph $G_P$GP. GPNM has become increasingly important in many applications, e.g., group finding and expert recommendation. In real scenarios, both $G_P$GP and $G_D$GD are updated frequently. However, the existing GPNM methods either need to perform a new GPNM procedure from scratch to deliver the node matching results based on the updated $G_P$GP and $G_D$GD or incrementally perform the GPNM procedure for each of the updates, leading to low efficiency. Although the elimination relations between updates and partitions of data graphs are considered in the state-of-the-art method, it still suffers from low efficiency as only the labels of nodes are considered in the partitions. Therefore, there is a pressing need for a new method to efficiently deliver the node matching results on the updated graphs. In this paper, we propose a new Partition-aware GPNM algorithm, called P-GPNM, where we propose two new partition methods, i.e., connection-based partition and density-based partition. In these two methods, P-GPNM considers the dense connections between partitions and the inner connections inside a single partition, respectively. The experimental results on five real-world social graphs demonstrate that our proposed P-GPNM is much more efficient than the state-of-the-art GPNM methods.

Cross-Domain Recommendation (CDR) and Cross-System Recommendation (CSR) have been proposed to improve the recommendation accuracy in a target dataset (domain/system) with the help of a source one with relatively richer information. However, most existing CDR and CSR approaches are single-target, namely, there is a single target dataset, which can only help the target dataset and thus cannot benefit the source dataset. In this paper, we focus on three new scenarios, i.e., Dual-Target CDR (DTCDR), Multi-Target CDR (MTCDR), and CDR+CSR, and aim to improve the recommendation accuracy in all datasets simultaneously for all scenarios. To do this, we propose a unified framework, called GA (based on Graph embedding and Attention techniques), for all three scenarios. In GA, we first construct separate heterogeneous graphs to generate more representative user and item embeddings. Then, we propose an element-wise attention mechanism to effectively combine the embeddings of common entities (users/items) learned from different datasets. Moreover, to avoid negative transfer, we further propose a Personalized training strategy to minimize the embedding difference of common entities between a richer dataset and a sparser dataset, deriving three new models, i.e., GA-DTCDR-P, GA-MTCDR-P, and GA-CDR+CSR-P, for the three scenarios respectively. Extensive experiments conducted on four real-world datasets demonstrate that our proposed GA models significantly outperform the state-of-the-art approaches.

An attributed dynamic graph contains multiple dynamic attributes associated with each edge in the graph. In attributed dynamic graph based applications, people usually can specify multiple constraints in the attributes to illustrate their requirements, such as the total cost, the total travel time and the stopover interval of a flight between two cities. This inspires the multi-constrained temporal path discovery in attributed dynamic graphs, which is a challenging NP-complete problem. To solve the problem, the existing methods adopt reinforcement learning with Monte Carlo tree search. However, these reinforcement learning based methods require a certain degree of “discovery experience” to obtain better results, which can lead to the expensive cost of query time and storage space, and thus are not applicable in real-time applications, e.g., route recommendations in a self-driving car. This motivates us to develop a new Adaptive Monte Carlo Tree Search algorithm, namely A-MCTS. A-MCTS dynamically adjusts the priority of historical records that are used in Monte Carlo tree search to improve the performance and reduce the size of required “discovery experience”. In addition, A-MCTS proposes a new adaptive replay memory structure that can store important historical records based on graph properties and optimize the consumption of storage space. The experimental results on ten real-world dynamic graphs demonstrate that the proposed A-MCTS outperforms the state-of-the-art methods in terms of both efficiency and effectiveness.

Dolomite dust waste (DDW) has the potential to be used as an expansive agent for mortar due to its richness in magnesium and calcium. This paper reports the possibility of developing low-cost expansive agent for mortar using DDW through various activation methods. The changes in the physicochemical properties of the activated DDW and the shrinkage resistance, flexural strength, and compressive strength of the composite mortar prepared by partially replacing cement were systematically investigated. The hydration products and microstructure of DDW-composite mortar were investigated by XRD and SEM-EDS techniques. This study confirmed the feasibility of activated DDW as mortar expansion agents and the necessity of activation treatment for the resourceful use of DDW. The results showed that the activation treatment enhanced the activity of DDW, and the higher hydration reactivity significantly improved the shrinkage resistance and mechanical properties of composite mortar compared to raw DDW. The addition of 10% C800 DDW (thermal at 800 °C) showed a full-age compensatory effect on the volume shrinkage of the mortar. Substituting cement partially with 10% C900 DDW (thermal at 900 °C), the volume expansion rate of composite mortar after 28 d of standard curing exhibited 24.49% higher than normal, and its compressive strength (40.1 MPa) at 60 d exceeded 6.40% than normal mortar (37.7 MPa). The drying shrinkage of G30-10 (mechanically activated) and A0.1-10 (chemically activated) at 60 d resulted in 6.23% and 5.19% lower than normal mortar, respectively. Microanalysis revealed that the addition of DDW promoted the generation of C-M-S-H gels. The findings are instructive for the preparation of green and low-cost mortar expanders using DDW.

Big graph data is different from traditional data and they usually contain complex relationships and multiple attributes. With the help of graph pattern matching, a pattern graph can be designed, satisfying special personal requirements and locate the subgraphs which match the required pattern. Then, how to locate a graph pattern with better attribute values in the big graph effectively and efficiently becomes a key problem to analyze and deal with big graph data, especially for a specific domain. This article introduces fuzziness into graph pattern matching. Then, a genetic algorithm, specifically an NSGA-II algorithm, and a particle swarm optimization algorithm are adopted for multi-fuzzy-objective optimization. Experimental results show that the proposed approaches outperform the existing approaches effectively.

Along with the fast development of network applications, network research has attracted more and more attention, where one of the most important research directions is networked multi-label classification. Based on it, unknown labels of nodes can be inferred by known labels of nodes in the neighborhood. As both the scale and complexity of networks are increasing, the problems of previously neglected system overhead are turning more and more seriously. In this article, a novel multi-objective optimization-based networked multi-label seed node selection algorithm (named as MOSS) is proposed to improve both the prediction accuracy for unknown labels of nodes from labels of seed nodes during classification and the system overhead for mining the labels of seed nodes with third parties before classification. Compared with other algorithms on several real networked data sets, MOSS algorithm not only greatly reduces the system overhead before classification but also improves the prediction accuracy during classification.

The assembly of nanorods with anisotropic interactions in dilute solution is studied using lattice dynamic Monte Carlo simulation. Each nanorod consists of two different beads with one lattice length apart. The anisotropic interactions are of orientational dependence, and two kinds of nearest-neighbor interactions are considered: (a) side-to-side attraction εxywhen two nanorods are parallel with head−head and tail−tail being nearest-neighbors and (b) end-to-end attraction εzwhen they are in end-to-head alignment. Three structures, wire, sheet, and pillar, are assembled by slowly cooling the system. Nanowires are assembled at large ratio r= εz/εxy, while sheets are assembled at small r. At intermediate values of r, three-dimensional (3D) pillars are formed. The aspect ratio Aof the 3D pillar increases with r, which can be expressed as A= 0.238r2.13 ± 0.05. The exponent is different from that of theoretical calculation, which is probably caused by a kinetic effect.