Shaojiang Wang's research while affiliated with Chinese Academy of Sciences and other places

Money laundering identification (MLI) is a challenging task for financial AI research and application due to its massive transaction volume, label sparseness, and label bias. Most of the existing MLI methods focus on individual-level abnormal behavior while neglecting the community factor that money laundering is a collaborative group crime. Furthermore, the massive volume of transactions and the issue of label shifting also impede the application of supervised or semi-supervised models. To this end, this paper proposes an efficient community-oriented algorithm, namely SEGE, to identify money laundering based on structural entropy minimization (SEM) with graph embedding in an unsupervised approach. Experiments on both a private real-world money laundering network and a public synthetic dataset show that our SEGE algorithm derives prominent performance and outperforms the parameterized learning-based graph representation methods. Moreover, we find that there are pervasive sub-communities in the real-world money laundering network. Based on our local algorithm, we propose a real combat strategy against the money laundering group, in which when we have several scattered suspicious accounts in the transaction network, we are able to retrieve the whole money laundering group by the union of sub-communities with both high precision and high recall rates.

In the above article [1] , the title has been modified as “Local Flow-Based Clustering on Directed Graphs: A Structural Entropy Minimization Approach,” where the word “local” is added.

Background: Due to the complex pathogenesis, the molecular mechanism of nonalcoholic steatohepatitis (NASH) remains unclear. In this study, we aimed to reveal the comprehensive metabolic and signaling pathways in the occurrence of NASH. Methods: C57BL/6 mice were treated with high-fat diet for 4 months to mimic the NASH phenotype. After the treatment, the physiochemical parameters were evaluated, and the liver tissues were prepared for untargeted metabolomic analysis with ultraperformance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry. Then, three relevant Gene Expression Omnibus (GEO) datasets were selected for integrative analysis of differentiated messenger RNA and metabolites. Results: The levels of phosphatidylethanolamine (PE) (16:1(9Z)/20:4(5Z,8Z,11Z,14Z)), oleic acid, and sphingomyelin (SM) (d18:0/12:0) were significantly increased, and the content of adenosine was severely reduced in NASH mice. The integrated interpretation of transcriptomic and metabolomic data indicated that the glycerophospholipid metabolism and necroptosis signaling were evidently affected in the development of NASH. The high level of SM (d18:0/12:0) may be related to the expression of acid sphingomyelinase (ASMase), and the elevated arachidonic acid was coordinated with the upregulation of cytosol phospholipase A2 (cPLA2) in the necroptosis pathway. Conclusions: In summary, the inflammatory response, necroptosis, and glycerophospholipid may serve as potential targets for mechanistic exploration and clinical practice in the treatment of NASH.

In this study, we focus on flow-based clustering on directed graphs and propose a localized algorithm for this problem. Flow-based clustering in networks requires a set of closely related vertices where the flow amount getting into it is larger than that going out of it. It is able to formulate a variety of practical problems, such as fund-raising set detection in financial networks and influential document clustering in citation networks, etc. Methodologically, we propose the new concept of two-dimensional structural entropy on directed graphs, and based on this, a local structural entropy minimization algorithm for detecting the flow-based community structure of networks is designed. We adopt our algorithm for the problem of fund-raising set detection in financial networks, in which vertices represent accounts, edges represent transactions between two accounts, and weights represent money amounts of transactions. In our experiments, the local two-dimensional structure entropy minimization algorithm is devoted to find a fund-raising community which involves a given input account. We conduct experiments on both synthetic and real fund-raising datasets. The experimental results demonstrate that, given a fixed account, our algorithm is able to efficiently locate a fund-raising community (if any) for which the fund flowing into the community is much higher than that flowing out, and the transactions within the community are relatively denser (fund amount based) than that of inter-community. For a synthetic ground-truth fund-raising community, we adjust the parameters to change its fund-raising tendency. The results for the synthetic datasets show that our algorithm obtains higher precision and recall rates as this tendency gets stronger with each single factor varing. For a real fund-raising community embedded in a simulated capital flow network, our algorithm also find it with high precision and recall rates. The experiments for both scenarios verify the effectiveness of our algorithm.

Given a set of radio broadcast programs, the radio broadcast scheduling problem is to allocate a set of devices to transmit the programs to achieve the optimal sound quality. In this article, we propose a complete algorithm to solve the problem, which is based on a branch-and-bound (BnB) algorithm. We formulate the problem with a new model, called constrained maximum weighted bipartite matching (CMBM), i.e., the maximum matching problem on a weighted bipartite graph with constraints. For the reduced matching problem, we propose a novel BnB algorithm by introducing three new strategies, including the highest quality first, the least conflict first and the more edge first. We also establish an upper bound estimating function for pruning the search space of the algorithm. The experimental results show that our new algorithm can quickly find the optimal solution for the radio broadcast scheduling problem at small scales, and has higher scalability for the problems at large scales than the existing complete algorithm.

In this paper, we propose the rectangle transformation problem (RTP) and its variants. RTP asks for a transformation by a rectangle partition between two rectangles of the same area. We are interested in the minimum RTP which requires to minimize the partition size. We mainly focus on the strict rectangle transformation problem (SRTP) in which rotation is not allowed in transforming. We show that SRTP has no finite solution if the ratio of the two parallel side lengths of input rectangles is irrational. So we turn to its complement denoted by SIRTP, in which case all side lengths can be assumed integral. We give a polynomial time algorithm ALGSIRTP which gives a solution at most $q/p+O(\sqrt{p})$ to SIRTP$(p,q)$ ($q\geq p$), where $p$ and $q$ are two integer side lengths of input rectangles $p\times q$ and $q\times p$, and so ALGSIRTP is a $O(\sqrt{p})$-approximation algorithm for minimum SIRTP$(p,q)$. On the other hand, we show that there is not constant solution to SIRTP$(p,q)$ for all integers $p$ and $q$ ($q>p$) even though the ratio $q/p$ is within any constant range. We also raise a series of open questions for the research along this line.