Xiaofeng Zhou

AAAI Conference 2026 Conference Paper

Beyond Single Transactions: D-EMAML---Dual-Edge Motif Neural Networks for Enhanced Anti-Money Laundering Detection

• Dongmei Han
• Min Min
• Yuchen Wang
• Guoming Xu
• Xiaofeng Zhou

Anti-money laundering (AML) detection is of vital importance in financial risk control. Although Graph Neural Networks (GNN) have yielded promising results, existing motif-based approaches primarily focus on node anomaly detection on simple graphs, which hinders the direct identification of anomalous edges in directed temporal transaction networks. Moreover, consecutive transaction relationships, termed dual-edge motifs, have rarely been considered in previous AML studies. To address these gaps, we propose the D-EMAML framework, which consists of: (1) Fast-Motif-Gen, a GPU-accelerated dual-edge motif graph generator with pruning; (2) D-EMGNN, an attention-enhanced heterogeneous GNN module that reduces motif-type information redundancy; (3) MELP, a label aggregation scheme projecting predictions from the motif graph to the original graph. Extensive experiments on real-world and synthetic datasets demonstrate significant improvements over representative baselines and validate the contribution of each component. To our knowledge, this is the first application of dual-edge motif graphs for GNN-based edge anomaly detection in AML.

TACAS Conference 2026 Conference Paper

EvolveGen: Algorithmic Level Hardware Model Checking Benchmark Generation through Reinforcement Learning

• Guangyu Hu
• Xiaofeng Zhou
• Wei Zhang
• Hongce Zhang

EAAI Journal 2026 Journal Article

Multi-feature fusion attention network for Chinese named entity recognition in Bucket Wheel Stacker-Reclaimer maintenance fault records

• Zhenkai Yang
• Xinyu Bo
• Jianhong Yang
• Debin Yang
• Xiaofeng Zhou

Knowledge graphs (KGs) are a pivotal technology for intelligent fault diagnosis of Bucket Wheel Stacker-Reclaimers (BWSRs), and Chinese Named Entity Recognition (NER) is a fundamental prerequisite for automatically constructing such KGs from maintenance fault records. Unlike standard corpora, unstructured BWSR fault records contain a heterogeneous mixture of colloquial expressions, domain-specific terminology, and mixed-code expressions, which requires jointly modeling local boundary cues and global contextual semantics. Existing Chinese NER methods mainly focus on multi-feature augmentation but lack effective mechanisms for dynamic multi-feature fusion, which limits their performance on fault records. To address this problem, we construct a dedicated Chinese NER corpus from real BWSR fault records and propose a Multi-Feature Fusion Attention Network (MF-FAN) with a dynamic fusion attention mechanism tailored for industrial fault records. MF-FAN jointly uses character and bigram lexicon embeddings as inputs, employs parallel Transformer and Dynamic Convolutional Neural Network (DCNN) branches to extract global contextual and local dependency features, and dynamically integrates them through an attention-based fusion mechanism at the token level. In the decoding layer, a linear layer followed by a Conditional Random Field (CRF) layer is used to model label transitions and output the globally optimal tag sequence. Experiments on four datasets show that MF-FAN achieves an F1-score of 79. 96% on the self-constructed BWSR-NER dataset and up to 96. 16% on public benchmarks, consistently outperforming seven strong baselines. This approach provides an efficient and scalable solution for automated KG construction from unstructured industrial texts, facilitating intelligent fault diagnosis and maintenance in real-world industrial scenarios.

EAAI Journal 2026 Journal Article

Weight prediction of the oxidation film in aircraft aluminium alloy components with small samples using data augmentation and random forest

• Shuai Li
• Zhuo Yu
• Yudong Chen
• Jiaqi Mai
• Xiaofeng Zhou
• Weichen Yu
• Yigeng Wang

Anodic oxidation stands as one of the pivotal processes in the surface modification of aircraft aluminum alloy components. The weight of the oxidation film typically exerts an influence on the comprehensive performance of the components, which also significantly impacts the service life of diverse aircrafts. Nevertheless, the intricate coupling characteristics stemming from multiple process parameters and small sample sizes present formidable challenges to the weight prediction of the oxidation film. In response to these issues, this study develops a weight prediction method of oxidation film using data augmentation and random forest (RF). Initially, given the scarcity of oxidation film weight data, this study designs a data augmentation method using quadratic B-spline interpolation and generative adversarial network (GAN) to augment the quantity of data and enhance representational capabilities. Subsequently, to assess the quality of the augmented data, a comprehensive evaluation index (CEI) using mean squared error (MSE) and Kullback-Leibler (KL) divergence is presented. Finally, considering complex coupling characteristics of process parameters, a weight prediction model using attention mechanism (AM) and RF is built to enhance the prediction performance. The results of data augmentation and oxidation film weight prediction in the actual anodic oxidation process of aircraft aluminum alloy component demonstate the feasibility and effectiveness.

EAAI Journal 2023 Journal Article

Feature selection using a sinusoidal sequence combined with mutual information

• Gaoteng Yuan
• Lu Lu
• Xiaofeng Zhou

Data classification is the most common task in machine learning, and feature selection is the key step in the classification task. Common feature selection methods mainly analyze the maximum correlation and minimum redundancy between feature factors and tags while ignoring the impact of the number of key features, which will inevitably lead to waste in subsequent classification training. To solve this problem, a feature selection algorithm (SSMI) based on the combination of sinusoidal sequences and mutual information is proposed. First, the mutual information between each feature and tag is calculated, and the interference information in high-dimensional data is removed according to the mutual information value. Second, a sine function is constructed, and sine ordering is carried out according to the mutual information value and feature mean value between different categories of the same feature. By adjusting the period and phase value of the sequence, the feature set with the largest difference is found, and the subset of key features is obtained. Finally, three machine learning classifiers (KNN, RF, SVM) are used to classify key feature subsets, and several feature selection algorithms (JMI, mRMR, CMIM, SFS, etc.) are compared to verify the advantages and disadvantages of different algorithms. Compared with other feature selection methods, the SSMI algorithm obtains the least number of key features, with an average reduction of 15 features. The average classification accuracy has been improved by 3% on the KNN classifier. On the HBV and SDHR datasets, the SSMI algorithm achieved classification accuracy of 81. 26% and 83. 12%, with sensitivity and specificity results of 76. 28%, 87. 39% and 68. 14%, 86. 11%, respectively. This shows that the SSMI algorithm can achieve higher classification accuracy with a smaller feature subset.