While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn ...informative and discriminative full-precision representations, raising concerns about computation, memory footprint, and energy consumption burden (largely overlooked) for real-world applications. This work explores a promising direction for graph contrastive learning (GCL) with spiking neural networks (SNNs), which leverage sparse and binary characteristics to learn more biologically plausible and compact representations. We propose SpikeGCL, a novel GCL framework to learn binarized 1-bit representations for graphs, making balanced trade-offs between efficiency and performance. We provide theoretical guarantees to demonstrate that SpikeGCL has comparable expressiveness with its full-precision counterparts. Experimental results demonstrate that, with nearly 32x representation storage compression, SpikeGCL is either comparable to or outperforms many fancy state-of-the-art supervised and self-supervised methods across several graph benchmarks.
Over the past few years, graph neural networks (GNNs) have become powerful and practical tools for learning on (static) graph-structure data. However, many real-world applications, such as social ...networks and e-commerce, involve temporal graphs where nodes and edges are dynamically evolving. Temporal graph neural networks (TGNNs) have progressively emerged as an extension of GNNs to address time-evolving graphs and have gradually become a trending research topic in both academics and industry. Advancing research and application in such an emerging field necessitates the development of new tools to compose TGNN models and unify their different schemes for dealing with temporal graphs. In this work, we introduce LasTGL, an industrial framework that integrates unified and extensible implementations of common temporal graph learning algorithms for various advanced tasks. The purpose of LasTGL is to provide the essential building blocks for solving temporal graph learning tasks, focusing on the guiding principles of user-friendliness and quick prototyping on which PyTorch is based. In particular, LasTGL provides comprehensive temporal graph datasets, TGNN models and utilities along with well-documented tutorials, making it suitable for both absolute beginners and expert deep learning practitioners alike.
Real-world graphs are typically complex, exhibiting heterogeneity in the
global structure, as well as strong heterophily within local neighborhoods.
While a growing body of literature has revealed ...the limitations of common graph
neural networks (GNNs) in handling homogeneous graphs with heterophily, little
work has been conducted on investigating the heterophily properties in the
context of heterogeneous graphs. To bridge this research gap, we identify the
heterophily in heterogeneous graphs using metapaths and propose two practical
metrics to quantitatively describe the levels of heterophily. Through in-depth
investigations on several real-world heterogeneous graphs exhibiting varying
levels of heterophily, we have observed that heterogeneous graph neural
networks (HGNNs), which inherit many mechanisms from GNNs designed for
homogeneous graphs, fail to generalize to heterogeneous graphs with heterophily
or low level of homophily. To address the challenge, we present Hetero$^2$Net,
a heterophily-aware HGNN that incorporates both masked metapath prediction and
masked label prediction tasks to effectively and flexibly handle both
homophilic and heterophilic heterogeneous graphs. We evaluate the performance
of Hetero$^2$Net on five real-world heterogeneous graph benchmarks with varying
levels of heterophily. The results demonstrate that Hetero$^2$Net outperforms
strong baselines in the semi-supervised node classification task, providing
valuable insights into effectively handling more complex heterogeneous graphs.
A sol–gel process based primarily on inorganic reagents as raw material was employed to synthesize the solid-electrolyte material of NASICON. The synthesizing process and the resulted material were ...characterized by means of TG, DTA, XRD and FT-IR. The results indicated that the sintering reaction could be completed at around 900
°C within 8
h without the detectable appearance of ZrO
2 phase. Furthermore, the resulted solid-electrolyte was used as the basic material for the fabrication of a planar-type CO
2. The measurements showed that the output electromotive force (EMF) followed Nernst equation well in CO
2 volume concentration ranging from 0.01% to 0.1% and its response and recovery time was less than 15 and 28
s, respectively. In order to enhance the resistance from other gases such as sulfide, H
2, CH
4, CO, humidity and so on, a noble metal doped active carbon cap was utilized in package, its filtering effect was investigated as well.
With the more and more extensive application of blockchain, blockchain security has been widely concerned by the society and deeply studied by scholars. Moreover, the security of blockchain data ...directly affects the security of various applications of blockchain. In this survey, we perform a comprehensive classification and summary of the security of blockchain data. First, we present classification of blockchain data attacks. Subsequently, we present the attacks and defenses of blockchain data in terms of privacy, availability, integrity and controllability. Data privacy attacks present data leakage or data obtained by attackers through analysis. Data availability attacks present abnormal or incorrect access to blockchain data. Data integrity attacks present blockchain data being tampered. Data controllability attacks present blockchain data accidentally manipulated by smart contract vulnerability. Finally, we present several important open research directions to identify follow-up studies in this area.
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literature has revealed ...the limitations of common graph neural networks (GNNs) in handling homogeneous graphs with heterophily, little work has been conducted on investigating the heterophily properties in the context of heterogeneous graphs. To bridge this research gap, we identify the heterophily in heterogeneous graphs using metapaths and propose two practical metrics to quantitatively describe the levels of heterophily. Through in-depth investigations on several real-world heterogeneous graphs exhibiting varying levels of heterophily, we have observed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, fail to generalize to heterogeneous graphs with heterophily or low level of homophily. To address the challenge, we present Hetero\(^2\)Net, a heterophily-aware HGNN that incorporates both masked metapath prediction and masked label prediction tasks to effectively and flexibly handle both homophilic and heterophilic heterogeneous graphs. We evaluate the performance of Hetero\(^2\)Net on five real-world heterogeneous graph benchmarks with varying levels of heterophily. The results demonstrate that Hetero\(^2\)Net outperforms strong baselines in the semi-supervised node classification task, providing valuable insights into effectively handling more complex heterogeneous graphs.
Two-dimensional (2D) crystals have renewed opportunities in design and assembly of artificial lattices without the constraints of epitaxy. However, the lack of thickness control in exfoliated van der ...Waals (vdW) layers prevents realization of repeat units with high fidelity. Recent availability of uniform, wafer-scale samples permits engineering of both electronic and optical dispersions in stacks of disparate 2D layers with multiple repeating units. We present optical dispersion engineering in a superlattice structure comprised of alternating layers of 2D excitonic chalcogenides and dielectric insulators. By carefully designing the unit cell parameters, we demonstrate > 90 % narrowband absorption in < 4 nm active layer excitonic absorber medium at room temperature, concurrently with enhanced photoluminescence in cm2 samples. These superlattices show evidence of strong light-matter coupling and exciton-polariton formation with geometry-tunable coupling constants. Our results demonstrate proof of concept structures with engineered optical properties and pave the way for a broad class of scalable, designer optical metamaterials from atomically-thin layers.
Solid electrolyte material of NASICON (sodium super ionic conductor) was synthesized through a modified solgel process. With the complex effect of oxalic acid added in synthesis, the stability of ...NASICON precursor solution was apparently improved and the crystallized NASICON phase was successfully achieved at the sintering temperature of 900DGC. X-ray diffraction (XRD) , Field-Emission Scanning Electronic Microscope (FE-SEM) and impedance spectrum (IS) were utilized to characterize the synthesized material. Making use of its favorite ion conductivity, a NASICON pellet type CO2 sensor was prepared. The experiments indicated that the sintering temperature has an important influence on its sensing property. With a suitable choice of the sintering condition for the NASICON pellet, a linear relationship of the output electromotive force (EMF) with the target gas concentration for the resulted CO2 sensor was well demonstrated in the volume gas concentration range of 0.01%1DG/x. The typical sensitivity is about 65 mV corresponding to a decade change of gas concentration, and the response and recovery time corresponding to 90% output EMF change is 15 s and 28 s, respectively.
Solid electrolyte material of NASICON (sodium super ionic conductor) was synthesized through a modified sol-gel process. With the complex effect of oxalic acid added in synthesis, the stability of ...NASICON precursor solution was apparently improved and the crystallized NASICON phase was successfully achieved at the sintering temperature of 900°C. X-ray diffraction (XRD), Field-Emission Scanning Electronic Microscope (FE-SEM) and impedance spectrum (IS) were utilized to characterize the synthesized material. Making use of its favorite ion conductivity, a NASICON pellet type CO2 sensor was prepared. The experiments indicated that the sintering temperature has an important influence on its sensing property. With a suitable choice of the sintering condition for the NASICON pellet, a linear relationship of the output electromotive force (EMF) with the target gas concentration for the resulted CO2 sensor was well demonstrated in the volume gas concentration range of 0.01%-1%. The typical sensitivity is about 65 mV corresponding to a decade change of gas concentration, and the response and recovery time corresponding to 90% output EMF change is 15 s and 28 s, respectively.