Graph representation learning (GRL) aims to map a graph into a low-dimensional vector space while preserving graph topology and node properties. This study proposes a novel GRL model, Multi-Level GRL (simply, ML-GRL), that recursively partitions input graphs by selecting the most appropriate community detection algorithm at each graph or partitioned subgraph. To preserve the relationship between subgraphs, ML-GRL incorporates global graphs that effectively maintain the overall topology. ML-GRL employs a prediction model, which is pre-trained using graph-based features and covers a wide range of graph distributions, to estimate GRL accuracy of each community detection algorithm without partitioning graphs or subgraphs and evaluating them. ML-GRL improves learning accuracy by selecting the most effective community detection algorithm while enhancing learning efficiency from parallel processing of partitioned subgraphs. Through extensive experiments with two different tasks, we demonstrate ML-GRL's superiority over the six representative GRL models in terms of both learning accuracy and efficiency. Specifically, ML-GRL not only improves the accuracy of existing GRL models by 3.68 ~ 47.59% for link prediction and 1.75 ~ 40.90% for node classification but also significantly reduces their running time by 9.63 ~ 62.71% and 7.14 ~ 82.14%, respectively. Our source code is available at https://github.com/pnpy6elp/Multi_Level_GRL.

The precise correction of outliers within radar rainfall data is crucial for a wide range of applications, including the analysis of extreme rainfall events, hydrological modeling, and the forecasting and warning of flash floods. Despite its significance, the challenge of correcting these outliers has not yet been fully explored, mainly due to the high dimensionality and spatiotemporal intricacies of radar rainfall data. Furthermore, most existing techniques for outlier correction are overly simplistic, revealing limitations when it comes to effectively correcting sporadic outliers. In response, this study has developed a novel approach of detecting and correcting outliers based on radar rainfall statistics at local spatiotemporal scale. In this approach, an algorithm of detecting outliers based on the simple 3-sigma rule in spatiotemporal context and an algorithm of detecting abrupt change between adjacent radar cells in spatial context, all in local scale, are iterated to enhance the quality of radar rainfall data progressively and effectively. This correction method resulted in a radar rainfall data with the grid cell value closely resembling that of the ground gauge data as well as the probability distribution. In addition, when compared to the existing methods, it demonstrated its ability to selectively remove only the outliers while preserving the integrity of the normal data. What sets this proposed method apart is not only its practicality, as it relies solely on 2D radar reflectivity data and can be easily implemented, but also its contribution to improving the analysis accuracy across various domains reliant on radar rainfall data.

With the advent of advanced metering infrastructure (AMI) technologies, various energy sources, such as gas, heating, and water can be actively collected. In this study, using multienergy sources, we aim to improve a prediction model for the consumption of a target energy source by exploiting the inherent correlations with other energy sources, which is a unique feature of the problem in this study. To achieve this, we propose a learning model based on a correlation-guided attention mechanism. We design our model with a two-stage learning strategy, wherein the model learns through two kinds of distinct loss functions, effectively capturing the correlations among energy sources and incorporating the learned weights into the prediction model. Through extensive experiments using real-world datasets, we demonstrate the effectiveness of our model based on six distinct types of neural network-based models while varying target energy sources, the used energy sources, and datasets.

In this study, we propose a novel graph representation learning (GRL) model, called Two-Level GRL with Subgraph-as-a-Node (SaaN 2L-GRL in short), that partitions input graphs into smaller subgraphs for effective and scalable GRL in two levels: 1) local GRL and 2) global GRL. To realize the two-level GRL in an efficient manner, we propose an abstracted graph, called Subgraph-as-a-Node Graph (SaaN in short), to effectively maintain the high-level graph topology while significantly reducing the size of the graph. By applying the SaaN graph to both local and global GRL, SaaN 2L-GRL can effectively preserve the overall structure of the entire graph while precisely representing the nodes within each subgraph. Through time complexity analysis, we confirm that SaaN 2L-GRL significantly reduces the learning time of existing GRL models by using the SaaN graph for global GRL, instead of using the original graph, and processing local GRL on subgraphs in parallel. Our extensive experiments show that SaaN 2L-GRL outperforms existing GRL models in both accuracy and efficiency. In addition, we show the effectiveness of SaaN 2L-GRL using diverse kinds of graph partitioning methods, including five community detection algorithms and representative edge- and vertex-cut algorithms.

In this paper, we propose a novel graph representation learning (GRL) model that aims to improve both representation accuracy and learning efficiency. We design a Two-Level GRL architecture based on the graph partitioning: 1) local GRL on nodes within each partitioned subgraph and 2) global GRL on subgraphs. By partitioning the graph through community detection, we enable elaborate node learning in the same community. Based on Two-Level GRL, we introduce an abstracted graph, Community-as-a-Node Graph(CaaN), to effectively maintain the high-level structure with a significantly reduced graph. By applying the CaaN graph to local and global GRL, we propose Two-Level GRL with Community-as-a-Node (CaaN 2L) that effectively maintains the global structure of the entire graph while accurately representing the nodes in each community. A salient point of the proposed model is that it can be applied to any existing GRL model by adopting it as the base model for local and global GRL. Through extensive experiments employing seven popular GRL models, we show that our model outperforms them in both accuracy and efficiency.

III-V and germanium (Ge) field-effect transistors (FETs) have been studied as candidates for post Si CMOS. In this paper, the performance of various digital blocks and static random access memory (SRAM) with different combinations of Si, III-V and Ge devices are studied. SPICE-compatible III-V n-channel FET (nFET) and Ge p-channel FET (pFET) models are developed for the analysis. The delay and energy of the different combinations are estimated and compared. In typical digital design, the driving capability of the nFET and pFET should be matched for optimum noise margin and performance. The combination of III-V nFET with low input capacitance and Ge pFET achieves the best energy-delay performance for many digital logic circuits. The read margin of SRAM is maximized with a Si pass-gate, and an inverter of III-V nFET and Ge pFET.