MAFI: GNN-Based Multiple Aggregators and Feature Interactions Network for Fraud Detection Over Heterogeneous Graph

SCN_GNN: A GNN-based fraud detection algorithm combining strong node and graph topology information

Graph Neural Networks (GNNs) have become the state-of-the-art method for many applications on graph structured data. GNNs are a model for graph representation learning, which aims at learning to generate low dimensional node embeddings that encapsulate structural and feature-related information. GNNs are usually trained in an end-to-end fashion, leading to highly specialized node embeddings. While this approach achieves great results in the single-task setting, the generation of node embeddings that can be used to perform multiple tasks (with performance comparable to single-task models) is still an open problem. We propose the use of meta-learning to allow the training of a GNN model capable of producing multi-task node embeddings. In particular, we exploit the properties of optimization-based meta-learning to learn GNNs that can produce general node representations by learning parameters that can quickly (i.e. with a few steps of gradient descent) adapt to multiple tasks. Our experiments show that the embeddings produced by a model trained with our purposely designed meta-learning procedure can be used to perform multiple tasks with comparable or, surprisingly, even higher performance than both single-task and multi-task end-to-end models.

Heterogeneous graphs are an essential structure that models real-world data through different types of nodes and relationships between them, including multimodality, which comprises different types of data such as text, image, and audio. Graph Neural Networks (GNNs) are a prominent graph representation learning method that takes advantage of the graph structure and its attributes that, when applied to the multimodal heterogeneous graph, learn a unique semantic space for the different modalities. Consequently, it allows multimodal fusion through simple operators such as sum, average, or multiplication, generating unified representations considering the supplementary and complementarity relationships between the modalities. In multimodal heterogeneous graphs, the labeling process tends to be even more costly due to the multiple modalities analyzed, in addition to the imbalance of classes inherent to some applications. In order to overcome these problems in applications that comprise a class of interest, One-Class Learning (OCL) is used. Given the lack of studies on multimodal early fusion in heterogeneous graphs for OCL tasks, we proposed a method based on unsupervised GNN for heterogeneous graphs and evaluated different early fusion operators. In this paper, we extend another work by evaluating the behavior of the main GNN convolutions in the method. We highlight that using operators such as average, addition, and subtraction were the best early fusion operators. In addition, GNN layers that do not use an attention mechanism performed better. In this way, we argue for heterogeneous graph neural networks in multimodal using early fusion simple operators instead of well-often-used concatenation and less complex convolutions.

Path-aware multi-hop graph towards improving graph learning

Most existing graph neural networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with the test set. In reality, the test data are not even available during the training process, making selection bias agnostic. Training GNNs with biased selected nodes leads to significant parameter estimation bias and greatly impacts the generalization ability on test nodes. In this article, we first present an experimental investigation, which clearly shows that the selection bias drastically hinders the generalization ability of GNNs, and theoretically proves that the selection bias will cause the biased estimation on GNN parameters. Then to remove the bias in GNN estimation, we propose a novel debiased GNNs (DGNN) with a differentiated decorrelation regularizer. The differentiated decorrelation regularizer estimates a sample weight for each labeled node such that the spurious correlation of learned embeddings could be eliminated. We analyze the regularizer in causal view and it motivates us to differentiate the weights of the variables based on their contribution to the confounding bias. Then, these sample weights are used for reweighting GNNs to eliminate the estimation bias, and thus, help to improve the stability of prediction on unknown test nodes. Comprehensive experiments are conducted on several challenging graph datasets with two kinds of label selection biases. The results well verify that our proposed model outperforms the state-of-the-art methods and DGNN is a flexible framework to enhance existing GNNs.

Graph neural network, as a powerful graph representation technique based on deep learning, has shown superior performance and attracted considerable research interest. However, it has not been fully considered in graph neural network for heterogeneous graph which contains different types of nodes and links. The heterogeneity and rich semantic information bring great challenges for designing a graph neural network for heterogeneous graph. Recently, one of the most exciting advancements in deep learning is the attention mechanism, whose great potential has been well demonstrated in various areas. In this paper, we first propose a novel heterogeneous graph neural network based on the hierarchical attention, including node-level and semantic-level attentions. Specifically, the node-level attention aims to learn the importance between a node and its metapath based neighbors, while the semantic-level attention is able to learn the importance of different meta-paths. With the learned importance from both node-level and semantic-level attention, the importance of node and meta-path can be fully considered. Then the proposed model can generate node embedding by aggregating features from meta-path based neighbors in a hierarchical manner. Extensive experimental results on three real-world heterogeneous graphs not only show the superior performance of our proposed model over the state-of-the-arts, but also demonstrate its potentially good interpretability for graph analysis.

Heterogeneous Graph Neural Networks (HGNNs) have demonstrated remarkable capabilities in capturing effective information in heterogeneous graphs, achieving outstanding performance in various learning tasks. However, the heavy dependency of HGNNs on neighbors information may result in high latency, which restricts their practicality in real-world applications. Recent studies have attempted to overcome such latency in Graph Neural Networks (GNNs) by distilling knowledge into student models that do not rely on graph structure. But these approaches primarily focus on replicating teachers' predictive outcomes while neglecting the structural knowledge they encoded. This limitation makes such approach less effective when graphs become complex, particularly on heterogeneous graphs. Motivated by this challenge, we propose HGKD, a novel hierarchical knowledge distillation framework that transfers both structural knowledge and predictive outcomes from HGNN teachers to a multi-layer perceptron student. Additionally, we provide two variants of HGKD that help the student learn from multiple teacher models through Pareto learning and incorporate low-cost neighbor information. We evaluate HGKD and its variants on a range of heterogeneous graph datasets. The results demonstrate that our student model achieves performance comparable to or exceeding that of HGNN teachers, despite not relying on graph structures during inference.

This paper addresses the critical challenge of fraud detection in medical insurance claims-a pervasive issue causing significant financial losses in healthcare-using Graph Neural Networks (GNNs). Given the intricate nature of healthcare data, traditional fraud detection methods do not inherently capture the complex relationships and patterns among different entities. We explore the potential of GNNs to effectively identify fraudulent claims by modeling the interactions among various entities-such as patients, healthcare providers, diagnoses, and services-as a heterogeneous graph. We employ two state-of-the-art heterogeneous GNN architectures, HINormer (Heterogeneous Information Network Transformer) and HybridGNN, along with a modified homogeneous GNN, RE-GraphSAGE (GraphSAGE "Graph Sample and Aggregate" with relation embeddings), adapted to handle the heterogeneity of healthcare data. The models are evaluated on real-world claims datasets of different sizes, comprising millions of medical activities. For the small-size claims dataset, the HINormer architecture followed by the RE-GraphSAGE architecture achieved the highest F-score (84% and 83%, respectively). For the medium-sized claims dataset, RE-GraphSAGE followed by HINormer achieved the highest F-score (84% and 81%, respectively), and for the large-size claims dataset, HINormer followed by RE-GraphSAGE achieved the highest F-score (82% and 79%, respectively). Additionally, we apply explainability techniques, namely GNNExplainer and PGExplainer, to provide insights into the models' decision-making processes and to examine their medical significance.

Graph Neural Networks (GNNs) have been increasingly deployed in a plethora of applications. However, the graph data used for training may contain sensitive personal information of the involved individuals. Once trained, GNNs typically encode such information in their learnable parameters. As a consequence, privacy leakage may happen when the trained GNNs are deployed and exposed to potential attackers. Facing such a threat, machine unlearning for GNNs has become an emerging technique that aims to remove certain personal information from a trained GNN. Among these techniques, certified unlearning stands out, as it provides a solid theoretical guarantee of the information removal effectiveness. Nevertheless, most of the existing certified unlearning methods for GNNs are only designed to handle node and edge unlearning requests. Meanwhile, these approaches are usually tailored for either a specific design of GNN or a specially designed training objective. These disadvantages significantly jeopardize their flexibility. In this paper, we propose a principled framework named IDEA to achieve flexible and certified unlearning for GNNs. Specifically, we first instantiate four types of unlearning requests on graphs, and then we propose an approximation approach to flexibly handle these unlearning requests over diverse GNNs. We further provide theoretical guarantee of the effectiveness for the proposed approach as a certification. Different from existing alternatives, IDEA is not designed for any specific GNNs or optimization objectives to perform certified unlearning, and thus can be easily generalized. Extensive experiments on real-world datasets demonstrate the superiority of IDEA in multiple key perspectives.

Network representation learning is receiving increasing attention from scholars. Among them, methods based on graph neural networks have become particularly popular. However, most existing methods currently only focus on networks with a single type of relations. In the real world, networks contain a wealth of diverse information, with multiple types of relationships between nodes. In this paper, we propose a graph neural network-based multiplex network representation learning model (GNMRL). We model nodes within each layer of the multiplex network by aggregating neighbor information. Additionally, since nodes are influenced by different network layers, we integrate node interaction information across network layers. We conducted systematic experiments on four datasets, and the results show that GNMRL outperforms other comparison methods in both link prediction and node classification tasks.

Graph Neural Networks (GNNs) have demonstrated significant success in various graph-related tasks. However, their performance is highly dependent on the availability of sufficient, class-balanced annotated data and an accurate graph structure. GNNs are vulnerable to substantial performance degradation when confronted with limited annotated samples, class imbalance, or noisy graph structures. First, a Dual GNN learning framework is introduced for semi-supervised node classification under limited supervision. The framework comprises two GNN-based node prediction modules: a primary module, which uses the input graph structure to induce standard node embeddings and predictions, and an auxiliary module, which leverages spectral clustering to construct a new graph structure and learn new node embeddings and predictions. These modules collaborate to enable end-to-end learning of discriminative node representations. Next, a graph augmentation method called Graph Dual Mixup (GDM) is proposed for graph classification with scarce labels. GDM employs a graph structural auto-encoder to learn structural embeddings, applying mixup in the learned structural embedding space to generate new graph structures. Additionally, mixup is applied to input node features, generating node features for new graph instances. Together, these generated node features and graph structures contribute new graphs that increase the size and diversity of the labeled dataset, improving classification performance. To enhance robustness against adversarial attacks on graph structures, an Efficient Low-Rank GNN is introduced. This approach learns robust low-rank sparse graph structures through a two-stage process. In the first stage, Singular Value Decomposition is used to estimate a low-rank approximation of the graph structure. This estimate is refined in the second stage by jointly learning a low-rank sparse graph structure alongside the GNN model, resulting in enhanced robustness. Finally, to address class-imbalanced node classification, a Unified GNN Learning (Uni-GNN) framework is proposed. Uni-GNN integrates structural and semantic connectivity representations to extend the propagation of embeddings to non-adjacent structural neighbors and semantically similar nodes, facilitating the diffusion of discriminative information. Additionally, it incorporates a balanced pseudo-label generation mechanism to improve the representations of minority classes. Comprehensive evaluations on benchmark datasets demonstrate that these methods outperform state-of-the-art approaches and hold significant potential for advancing GNN learning with limited supervision.

In recent years, heterogeneous network/graph representation learning/embedding (HNE) has drawn tremendous attentions from research communities in multiple disciplines. HNE has shown its outstanding performances in various networked data analysis and mining tasks. In fact, most of real-world information networks in multiple fields can be modelled as the heterogeneous information networks (HIN). Thus, the HNE-based techniques can sufficiently capture rich-structured and semantic latent features from the given information network in order to facilitate for different task-driven learning tasks. This is considered as fundamental success of HNE-based approach in comparing with previous traditional homogeneous network/graph based embedding techniques. However, there are recent studies have also demonstrated that the heterogeneous network/graph modelling and embedding through graph neural network (GNN) is not usually reliable. This challenge is original come from the fact that most of real-world heterogeneous networks are considered as incomplete and normally contain a large number of feature noises. Therefore, multiple attempts have proposed recently to overcome this limitation. Within this approach, the meta-path-based heterogeneous graph-structured latent features and GNN-based parameters are jointly learnt and optimized during the embedding process. However, this integrated GNN and heterogeneous graph structure (HGS) learning approach still suffered a challenge of effectively parameterizing and fusing different graph-structured latent features from both GNN- and HGS-based sides into better task-driven friendly and noise-reduced embedding spaces. Therefore, in this paper we proposed a novel attention-supplemented heterogeneous graph structure embedding approach, called as: AGSE. Our proposed AGSE model supports to not only achieve the combined rich heterogeneous structural and GNN-based aggregated node representations but also transform achieved node embeddings into noise-reduced and task-driven friendly embedding space. Extensive experiments in benchmark heterogeneous networked datasets for node classification task showed the effectiveness of our proposed AGSE model in comparing with state-of-the-art network embedding baselines.

Graph neural networks (GNNs) have known an increasing success recently, with many GNN variants achieving state-of-the-art results on node and graph classification tasks. The proposed GNNs, however, often implement complex node and graph embedding schemes, which makes it challenging to explain their performance. In this paper, we investigate the link between a GNN’s expressiveness, that is, its ability to map different graphs to different representations, and its generalization performance in a graph classification setting. In particular, we propose a principled experimental procedure where we (i) define a practical measure for expressiveness, (ii) introduce an expressiveness-based loss function that we use to train a simple yet practical GNN that is permutation-invariant, (iii) illustrate our procedure on benchmark graph classification problems and on an original real-world application. Our results reveal that expressiveness alone does not guarantee a better performance, and that a powerful GNN should be able to produce graph representations that are well separated with respect to the class of the corresponding graphs.

Semi-supervised node classification on graph-structured data has many applications such as fraud detection, fake account and review detection, user’s private attribute inference in social networks, and community detection. Various methods such as pairwise Markov Random Fields (pMRF) and graph neural networks were developed for semi-supervised node classification. pMRF is more efficient than graph neural networks. However, existing pMRF-based methods are less accurate than graph neural networks, due to a key limitation that they assume a heuristics-based constant edge potential for all edges. In this work, we aim to address the key limitation of existing pMRF-based methods. In particular, we propose to learn edge potentials for pMRF. Our evaluation results on various types of graph datasets show that our optimized pMRF-based method consistently outperforms existing graph neural networks in terms of both accuracy and efficiency. Our results highlight that previous work may have underestimated the power of pMRF for semi-supervised node classification.

Industry 5.0 promotes the transformation of manufacturing toward flexibility, personalization, and sustainability. As a critical component of closed-loop manufacturing systems, disassembly operations urgently require more flexible and efficient human–robot collaboration models. To this end, this work, for the first time, proposes a multihuman–robot collaborative circular disassembly line balancing problem. By allowing workers to move between robotic workstations, the proposed system enhances operational flexibility. Furthermore, a multiworker mechanism is introduced to improve fault tolerance and system stability, overcoming the limitations of fixed worker positions in existing collaborative disassembly research. To solve this problem, we formulate a discrete-time mixed-integer programming model based on product AND/OR graphs, aiming to maximize disassembly profit. The model’s correctness is verified using CPLEX. Additionally, we develop a heterogeneous graph neural network-enhanced proximal policy optimization (PPO) algorithm. By integrating product and workstation information into a heterogeneous graph, the algorithm performs two-stage feature extraction and node embedding via graph neural networks. Based on these embeddings, the agent dynamically selects multiple actions per decision step to simulate the behavior of multiple workers moving simultaneously. Experimental results show that the proposed method outperforms traditional reinforcement learning algorithms such as PPO and deep Q-network algorithm in terms of disassembly profit. Moreover, it demonstrates strong generalization capability in cross-task transfer and scalability experiments involving different task graph sizes. The improved performance is achieved with acceptable computational time.