Tax evasion refers to the illegal act of taxpayers using deception and concealment to avoid paying taxes. How to detect tax evasion effectively is always an important topic for the government and academic researchers....
详细信息
ISBN:
(数字)9781728162515
ISBN:
(纸本)9781728162522
Tax evasion refers to the illegal act of taxpayers using deception and concealment to avoid paying taxes. How to detect tax evasion effectively is always an important topic for the government and academic researchers. Recent research has proposed using machine learning technologies to detect tax evasion and has achieved good results in some specific conditions. However, recent methods have three shortcomings. First, recent methods mainly use the basic features extracted based on expert experience. Second, recent methods do not make full use of the edge features of the transaction network. Third, recent methods cannot adapt to a dynamic transaction network. To overcome these challenges, we propose a novel tax evasion detection method, the temporal edge enhanced graph attention network (T-EGAT), which combines the edge enhanced graph attention network (EGAT) and the recurrent weighted average unit (RWA). Specifically, the EGAT is used to learn complex topological structures for capturing spatial dependence and the RWA is used to learn the dynamic changes of transaction data for capturing temporal dependence. Experimental tests using real-world tax data demonstrate that our method achieves better performance at detecting tax evaders than existing methods.
Algorithms that involve both forecasting and optimization are at the core of solutions to many difficult real-world problems, such as in supply chains (inventory optimization), traffic, and in the transition towards c...
详细信息
Background: Bio-entity Coreference resolution is an important task to gain a complete understanding of biomedical texts automatically. Previous neural network-based studies on this topic are domain system based method...
详细信息
Deep neural networks (DNNs) provide the best of class solutions to many supervised tasks due to their powerful function fitting capabilities. However, it is challenging to handle data bias, such as label noise and cla...
详细信息
ISBN:
(纸本)9781665423991
Deep neural networks (DNNs) provide the best of class solutions to many supervised tasks due to their powerful function fitting capabilities. However, it is challenging to handle data bias, such as label noise and class imbalance, when applying DNNs to solve real-world problems. Sample reweighting is a popular strategy to tackle data bias, which assigns higher weights to informative samples or samples with clean labels. However, conventional reweighting methods require prior knowledge of the distribution information of data bias, which is intractable in practice. In recent years, meta-learning-based methods have been proposed to learn to assign weights to training samples adaptively by using their online training loss or gradient directions. However, the latent bias distribution cannot be adequately characterized in an online fashion. The online loss distribution changes over the training procedure, making it even harder to perform the sample weight learning. In contrast to past methods, we propose a two-stage training strategy to tackle the above problems. In the first stage, the loss sequences of samples are collected. In the second stage, a subnet with convolutional layers is utilized to learn the mapping from offline sample loss sequence to sample weight adaptively. Guided by a small unbiased meta dataset, this subnet is optimized iteratively with the main classifier network in a meta-learning manner. Empirical results show that our method, called Meta Reweighting with Offline Loss Sequence (MROLS), outperforms state-of-the-art reweighting techniques on most benchmarks. Moreover, the weights of training samples learned via MROLS can be well utilized by other classifiers, which can directly enhance the standard training schema. Our source code is available at https://***/Neronjust2017/MROLS.
In April 2022, the Vistamilk SFI Research Centre organized the second edition of the "International Workshop on Spectroscopy and Chemometrics – Applications in Food and Agriculture". Within this event, a da...
详细信息
The grade of clear cell renal cell carcinoma (ccRCC) is a critical prognostic factor, making ccRCC nuclei grading a crucial task in RCC pathology analysis. computer-aided nuclei grading aims to improve pathologists...
详细信息
Histological subtype of papillary (p) renal cell carcinoma (RCC), type 1 vs. type 2, is an essential prognostic factor. The two subtypes of pRCC have a similar pattern, i.e., the papillary architecture, yet some subtl...
详细信息
In this research, we try to investigate a solar-geothermal energy system. This system includes three turbines for power production, a PEM electrolyzer for hydrogen production, and a thermoelectric for generating elect...
详细信息
Hyperspectral images (HSI) are crucial for remote sensing applications as they provide detailed spectral information that accurately identifies and analyzes various materials and land features. HSI classification face...
详细信息
Hyperspectral images (HSI) are crucial for remote sensing applications as they provide detailed spectral information that accurately identifies and analyzes various materials and land features. HSI classification faces challenges due to large data volumes and high dimensionality. Dimensionality reduction techniques help address these problems by simplifying model computation, reducing redundancy, and improving feature selection. However, traditional methods struggle to capture nonlinear structures and local–global relationships in hyperspectral data. We propose a new multi-feature fusion classification model called the Uniform Manifold Approximation and Projection (UMAP) and Simple Attention Module (SimAM) mechanism fusion network (UMAPSAMFN). The main workflow of the model consists of several steps. The network uses UMAP to map high-dimensional HSI data into a low-dimensional space while maintaining a local and global structure. The feature data are sent to the convolutional neural network (CNN) and graph convolutional network (GCN) modules to capture pixel-level features and contextual information. These data are separately processed through multi-head attention modules to enhance the ability to represent feature information. Finally, the processed data are jointly fed into a fusion module with an attention mechanism to boost feature information and achieve deep modeling results. The experimental results on three benchmark HSI datasets show that UMAPSAMFN consistently exhibits the highest classification accuracy, with overall classification accuracies of 93.28%, 96.13%, and 97.73% on the Indian Pines, Pavia University, and Salinas datasets, respectively.
Numerical computing of the rank of a matrix is a fundamental problem in scientific computation. The datasets generated by the internet often correspond to the analysis of high-dimensional sparse matrices. Notwithstand...
详细信息
暂无评论