The problem of extracting meaningful data through graph analysis spans a range of different fields, such as social networks, knowledge graphs, citation networks, the World Wide Web, and so on. As increasingly structured data become available, the importance of being able to effectively mine and learn from such data continues to grow. In this paper, we propose the multi-scale aggregation graph neural network based on feature similarity (MAGN), a novel graph neural network defined in the vertex domain. Our model provides a simple and general semi-supervised learning method for graph-structured data, in which only a very small part of the data is labeled as the training set. We first construct a similarity matrix by calculating the similarity of original features between all adjacent node pairs, and then generate a set of feature extractors utilizing the similarity matrix to perform multi-scale feature propagation on graphs. The output of multi-scale feature propagation is finally aggregated by using the mean-pooling operation. Our method aims to improve the model representation ability via multi-scale neighborhood aggregation based on feature similarity. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our method compared to a variety of popular architectures. 相似文献
The trend prediction of the stock is a main challenge. Accidental factors often lead to short-term sharp fluctuations in stock markets, deviating from the original normal trend. The short-term fluctuation of stock price has high noise, which is not conducive to the prediction of stock trends. Therefore, we used discrete wavelet transform (DWT)-based denoising to denoise stock data. Denoising the stock data assisted us to eliminate the influences of short-term random events on the continuous trend of the stock. The denoised data showed more stable trend characteristics and smoothness. Extreme learning machine (ELM) is one of the effective training algorithms for fully connected single-hidden-layer feedforward neural networks (SLFNs), which possesses the advantages of fast convergence, unique results, and it does not converge to a local minimum. Therefore, this paper proposed a combination of ELM- and DWT-based denoising to predict the trend of stocks. The proposed method was used to predict the trend of 400 stocks in China. The prediction results of the proposed method are a good proof of the efficacy of DWT-based denoising for stock trends, and showed an excellent performance compared to 12 machine learning algorithms (e.g., recurrent neural network (RNN) and long short-term memory (LSTM)). 相似文献
Instance matching is a key task in knowledge graph fusion, and it is critical to improving the efficiency of instance matching, given the increasing scale of knowledge graphs. Blocking algorithms selecting candidate instance pairs for comparison is one of the effective methods to achieve the goal. In this paper, we propose a novel blocking algorithm named MultiObJ, which constructs indexes for instances based on the Ordered Joint of Multiple Objects’ features to limit the number of candidate instance pairs. Based on MultiObJ, we further propose a distributed framework named Follow-the-Regular-Leader Instance Matching (FTRLIM), which matches instances between large-scale knowledge graphs with approximately linear time complexity. FTRLIM has participated in OAEI 2019 and achieved the best matching quality with significantly efficiency. In this research, we construct three data collections based on a real-world large-scale knowledge graph. Experiment results on the constructed data collections and two real-world datasets indicate that MultiObJ and FTRLIM outperform other state-of-the-art methods. 相似文献
Kinetics and Catalysis - Hierarchically porous γ-Al2O3, TiO2–Al2O3 composite supports, and Pt–Sn–K/Al2O3 and Pt–Sn–K/TiO2–Al2O3 catalysts were prepared... 相似文献
Carbon quantum dots (CQDs) co-doped with N, P and S derived from expired milk was prepared by a simple hydrothermal method. By dipping pure cotton face towel (PCFT) into CQDs ink, a flexible all-biomass CQDs/PCFT sensor was prepared for the first time. Due to the heteroatom doping, extremely small particle size of CQDs and excellent permeability of CQDs/PCFT film, the flexible CQDs/PCFT sensor showed the high sensitivity and bending stability. In the range of 0–60° bending states, the responses of CQDs/PCFT sensor to four target analytes changed by less 5.0%. After 3000 bending of 60°, the maximum change of the response to the target analytes was only 6.4%. Interestingly, due to the abundant functional groups and defects of CQDs, the flexible CQDs/PCFT sensor displayed sensing curves of different shapes for different target analytes. In this way, by establishing a database of sensing curves of target analytes, multiple analytes can be detected discriminatively by relying only on single sensor with the help of image recognition. This work provided a reference for the development of cotton fiber based all biomass flexible gas sensor.