Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modeling the attributed networks with GCN allows to capture the sparsity and nonlinearity, utilizing a deep neural network allows direct residual ing from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies.
published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rightsCopyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.• Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal.If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User
In the past years, many new explanation methods have been proposed to achieve interpretability of machine learning predictions. However, the utility of these methods in practical applications has not been researched extensively. In this paper we present the results of a human-grounded evaluation of SHAP, an explanation method that has been well-received in the XAI and related communities.In particular, we study whether this local model-agnostic explanation method can be useful for real human domain experts to assess the correctness of positive predictions, i.e. alerts generated by a classifier. We performed experimentation with three different groups of participants (159 in total), who had basic knowledge of explainable machine learning. We performed a qualitative analysis of recorded reflections of experiment participants performing alert processing with and without SHAP information. The results suggest that the SHAP explanations do impact the decision-making process, although the model's confidence score remains to be a leading source of evidence. We statistically test whether there is a significant difference in task utility metrics between tasks for which an explanation was available and tasks in which it was not provided. As opposed to common intuitions, we did not find a significant difference in alert processing performance when a SHAP explanation is available compared to when it is not.
Effectively detecting anomalous nodes in attributed networks is crucial for the success of many real-world applications such as fraud and intrusion detection. Existing approaches have difficulties with three major issues: sparsity and nonlinearity capturing, residual modeling, and network smoothing. We propose Residual Graph Convolutional Network (ResGCN), an attention-based deep residual modeling approach that can tackle these issues: modelling the attributed networks with GCN allows to capture the sparsity and nonlinearity; utilizing a deep neural network allows to directly learn residual from the input, and a residual-based attention mechanism reduces the adverse effect from anomalous nodes and prevents over-smoothing. Extensive experiments on several real-world attributed networks demonstrate the effectiveness of ResGCN in detecting anomalies.
II. We study some of the basic network characteristics in Section III. We explore meso-scale structural properties of the network, including k-cliques analysis in Section IV. We present a comparative analysis of the unique characteristics of the transaction network with other scale-free networks in Section V and, finally, discuss our findings and future directions in Section VI.Our main contributions are mentioned below.1) The anonymized banking transaction data of users. As per the best of our knowledge, this will be the first publicly available dataset of users' banking transactions.The dataset is available at https://github.com/akratiiet/ RaboBank Dataset. 2) We perform a detailed analysis of unweighted and weighted banking transaction networks and highlight the similarities and differences of these networks with other types of networks. As per the best of our knowledge, this is the first work to analyze intra-bank transaction network. We hope the shared data and this work will help further understand the evolution of money flow in society. II. DATASET AND NETWORKSThe dataset is collected from the Coöperatieve Rabobank U.A. 1 , a Dutch multinational banking and financial services company. This dataset consists of bank accounts and transactions between them. For any pairs of accounts with one or more transactions, we also collected more information, including the numbers of transactions between two accounts and the total amount of money transferred from one account to another over a period of 11 years from 2010 to 2020. Thus, it can be organized into a transaction network, either unweighted or weighted. The data was shared for 1,624,030 bank accounts and 4,127,043 transactions based on (from account, to account) pair.We create the network from this data, having 1,624,030 nodes which are accounts, and 3,823,167 edges which represent that the respective users performed one or more transactions. Next, we identify the weakly connected components in the network, and it contains 723 connected components, where the largest weakly connected component contains 1,622,173 nodes and 1 https://www.rabobank.nl/ Abstract-We construct a network of 1.6 million nodes from banking transactions of users of Rabobank. We assign two weights on each edge, which are the aggregate transferred amount and the total number of transactions between the users from the year 2010 to 2020. We present a detailed analysis of the unweighted and both weighted networks by examining their degree, strength, and weight distributions, as well as the topological assortativity and weighted assortativity, clustering, and weighted clustering, together with correlations between these quantities. We further study the meso-scale properties of the networks and compare them to a randomized reference system. This will be the first p ublicly s hared d ataset o f intra-bank transactions, and this work highlights the unique characteristics of banking transaction networks with other scale-free networks.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.