Graph neural networks (GNNs) have emerged as a powerful paradigm for embedding-based entity alignment due to their capability of identifying isomorphic subgraphs. However, in real knowledge graphs (KGs), the counterpart entities usually have non-isomorphic neighborhood structures, which easily causes GNNs to yield different representations for them. To tackle this problem, we propose a new KG alignment network, namely AliNet, aiming at mitigating the non-isomorphism of neighborhood structures in an end-to-end manner. As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures. It employs an attention mechanism to highlight helpful distant neighbors and reduce noises. Then, it controls the aggregation of both direct and distant neighborhood information using a gating mechanism. We further propose a relation loss to refine entity representations. We perform thorough experiments with detailed ablation studies and analyses on five entity alignment datasets, demonstrating the effectiveness of AliNet.
Problematic online game use (POGU) has become a serious global public health concern among adolescents. However, its influencing factors and mediating mechanisms remain largely unknown. This study provides the first longitudinal design to test stage-environment fit theory empirically in POGU. A total of 356 Chinese students reported on teacher autonomy support, basic psychological needs satisfaction, school engagement, and POGU in the autumn of their 7th-9th grade years. Path analyses supported the proposed pathway: 7th grade teacher autonomy support increased 8th grade basic psychological needs satisfaction, which in turn increased 9th grade school engagement, which ultimately decreased 9th grade POGU. Furthermore, 7th grade teacher autonomy support directly increased 9th grade school engagement, which in turn decreased 9th grade POGU. These findings suggest that teacher autonomy support is an important protective predictor of adolescent POGU, and basic psychological needs satisfaction and school engagement are the primary mediators in this association.
This paper proposes a simple but effective graph-based agglomerative algorithm, for clustering high-dimensional data. We explore the different roles of two fundamental concepts in graph theory, indegree and outdegree, in the context of clustering. The average indegree reflects the density near a sample, and the average outdegree characterizes the local geometry around a sample. Based on such insights, we define the affinity measure of clusters via the product of average indegree and average outdegree. The product-based affinity makes our algorithm robust to noise. The algorithm has three main advantages: good performance, easy implementation, and high computational efficiency. We test the algorithm on two fundamental computer vision problems: image clustering and object matching. Extensive experiments demonstrate that it outperforms the stateof-the-arts in both applications. 1 1 The code and supplemental materials are publicly available at
We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate "fewshot" models for classes existing at the tail of the class distribution, for which little data is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extraction model by coarse-tofine knowledge-aware attention mechanism. We demonstrate our results for a large-scale benchmark dataset which show that our approach significantly outperforms other baselines, especially for long-tail relations.1
Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show * Work done while at UZH.
A switched-capacitor interleaved bidirectional (SCIB) dc-dc converter that combines a three-phase interleaved structure with switched-capacitor cells is proposed. The converter features a wide-voltage-gain range, low current ripple on the low voltage side, low voltage stresses across power switches, an absolute common ground between input and output, and can be easily extended into a topology family. The operating principle and power switch voltage and current stresses are analyzed in detail. An 800W prototype with a wide voltage gain range (Uhigh=400V, Ulow=30-100V) is described, demonstrating a maximum efficiency of 95.8% in the step-up mode and 95.9% in the step-down mode. Index Terms-Bidirectional dc-dc converter, electric vehicles, super capacitor, three-phase interleaved, wide voltage gain range.
Metallic nanostructures with nanogap features are proved to be highly effective building blocks for plasmonic systems, as they can provide ultrastrong electromagnetic (EM) fields and controllable optical properties. A wide range of fields, including surface enhanced spectroscopy, sensing, imaging, nonlinear optics, optical trapping, and metamaterials, are benefited from these enhanced EM fields. This review outlines the latest development of the fabrication methods for nanogap structures (metal nanoparticle assembly, nanosphere lithography, electron beam lithography (EBL), focused ion beam (FIB) lithography, oblique angle shadow evaporation, edge lithography, and so on), followed by a summary of their optical applications. The present review will inspire more ingenious designs and fabrications of plasmonic nanogap structures with lithography‐free fabrication techniques, and promote their applications in optics and electronics.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.