Graph Neural Networks for Recommendation Leveraging Multimodal Information

Data in many real-world applications such as social networks, users shopping behaviors, and inter-item relationships can be represented as graphs. Graph Neural Networks (GNNs) have shown great success in learning meaningful representations for graphs by inherently integrating node information and topological structure. Data in social recommendations can also be denotes as graph data in the form of user-user social graphs and user-item graphs. In addition, the relationships between items can be denoted as item-item graphs. GNNs provide an unprecedented opportunity to advance social recommendations. However, there are tremendous challenges in building GNNs-based social recommendations where (1) users (items) are simultaneously involved in the user-item graph and user-user social graph (item-item graph); (2) user-item graphs not only contain user-item interactions but also include users’ opinions on items; and (3) the nature of social relations are heterogeneous among users. In this paper, we propose a novel graph neural network framework ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GraphRec+</b> ) for social recommendations, which is able to coherently model graph data in order to learn better user and item representations. Specifically, we introduce a principled approach for jointly capturing interactions and opinions in the user-item graph and also propose an attention mechanism to differentiate the heterogeneous strengths of social relations. Comprehensive experiments on three real-world datasets show the effectiveness of the proposed framework.

Ranging from Matrix Factorization to deep learning based methods, recommender systems usually obtain user's (or item's) embedding via mapping from existed features. However, the collaborative signal is not encoded in the embedding process. Graph Neural Networks (GNNs) have been proved to be powerful in learning on graph data. But building recommender systems on GNNs faces challenges: the user-item graph encodes both interactions and opinions; user item interactions have heterogeneous strengths. To address these challenges, we proposed a novel framework on collaborative filtering recommendation via attention mechanism (GCFA), which models heterogeneous user-item interaction strengths and exploits the user-item graph structure by propagating embeddings on it. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework GCFA.

Transparency and accountability have become major concerns for black-box machine learning (ML) models. Proper explanations for the model behavior increase model transparency and help researchers develop more accountable models. Graph neural networks (GNN) have recently shown superior performance in many graph ML problems than traditional methods, and explaining them has attracted increased interest. However, GNN explanation for link prediction (LP) is lacking in the literature. LP is an essential GNN task and corresponds to web applications like recommendation and sponsored search on web. Given existing GNN explanation methods only address node/graph-level tasks, we propose Path-based GNN Explanation for heterogeneous Link prediction (PaGE-Link) that generates explanations with connection interpretability, enjoys model scalability, and handles graph heterogeneity. Qualitatively, PaGE-Link can generate explanations as paths connecting a node pair, which naturally captures connections between the two nodes and easily transfer to human-interpretable explanations. Quantitatively, explanations generated by PaGE-Link improve AUC for recommendation on citation and user-item graphs by 9 - 35% and are chosen as better by 78.79% of responses in human evaluation.

Graph Neural Networks (GNNs) have achieved remarkable success by extending traditional convolution to learning on non-Euclidean data. The key to the GNNs is adopting the neural message-passing paradigm with two stages: aggregation and update. The current design of GNNs considers the topology information in the aggregation stage. However, in the updating stage, all nodes share the same updating function. The identical updating function treats each node embedding as i.i.d. random variables and thus ignores the implicit relationships between neighborhoods, which limits the capacity of the GNNs. The updating function is usually implemented with a linear transformation followed by a non-linear activation function. To make the updating function topology-aware, we inject the topological information into the non-linear activation function and propose Graph-adaptive Rectified Linear Unit (GReLU), which is a new parametric activation function incorporating the neighborhood information in a novel and efficient way. The parameters of GReLU are obtained from a hyperfunction based on both node features and the corresponding adjacent matrix. To reduce the risk of overfitting and the computational cost, we decompose the hyperfunction as two independent components for nodes and features respectively. We conduct comprehensive experiments to show that our plug-and-play GReLU method is efficient and effective given different GNN backbones and various downstream tasks.

Traffic forecasting is a crucial aspect of modern Intelligent Transportation Systems (ITS) and the Internet of Vehicles (IoV), playing a vital role in improving the safety and efficiency of daily transportation activities. Despite the valuable contributions of traditional machine learning (ML) models and advanced deep learning (DL) techniques, there persist challenges in capturing the intricate spatial and temporal dependencies inherent in traffic flow. In response to these challenges, we present GRAPHITE, an innovative framework that combines Graph Neural Networks (GNNs) and Generative Adversarial Networks (GANs) to leverage generative reasoning for efficient traffic management. Our model seamlessly integrates historical traffic volume data collected by road sensors with local spatial information encoded through knowledge graphs (KGs) associated with each sensor. These KGs offer a structured representation of relationships between traffic sensors and points of interest (POIs) in their neighborhood, thereby enhancing the comprehension of the urban context and leading to more accurate traffic predictions. Extensive experiments conducted on diverse datasets underscore the efficacy of GRAPHITE. Notably, we achieved a maximum decrease in RMSE of 31.05% compared to GAN-GRU and a maximum increase in R2 of 8.15% compared to GAN-RNN, positioning GRAPHITE as a standout solution among the current state-of-the-art approaches. Our code is available at: https://github.com/MODAL-UNINA/GRAPHITE.

Online users are typically active on multiple social media networks (SMNs), which constitute a multiplex social network. With improvements in cybersecurity awareness, users increasingly choose different usernames and provide different profiles on different SMNs. Thus, it is becoming increasingly challenging to determine whether given accounts on different SMNs belong to the same user; this can be expressed as an interlayer link prediction problem in a multiplex network. To address the challenge of predicting interlayer links, feature or structure information is leveraged. Existing methods that use network embedding techniques to address this problem focus on learning a mapping function to unify all nodes into a common latent representation space for prediction; positional relationships between unmatched nodes and their common matched neighbors (CMNs) are not utilized. Furthermore, the layers are often modeled as unweighted graphs, ignoring the strengths of the relationships between nodes. To address these limitations, we propose a framework based on multiple types of consistency between embedding vectors (MulCEVs). In MulCEV, the traditional embedding-based method is applied to obtain the degree of consistency between the vectors representing the unmatched nodes, and a proposed distance consistency index based on the positions of nodes in each latent space provides additional clues for prediction. By associating these two types of consistency, the effective information in the latent spaces is fully utilized. In addition, MulCEV models the layers as weighted graphs to obtain representation. In this way, the higher the strength of the relationship between nodes, the more similar their embedding vectors in the latent representation space will be. The results of our experiments on several real-world and synthetic datasets demonstrate that the proposed MulCEV framework markedly outperforms current embedding-based methods, especially when the number of training iterations is small.

The graph neural network (GNN) has recently become an emerging research topic for processing non-euclidean data structures since the data used in various popular application domains are usually modeled as a graph, such as social networks, recommendation systems, and computer vision. Previous GNN accelerators commonly utilize the hybrid architecture to resolve the issue of “hybrid computing pattern” in GNN training. Nevertheless, the hybrid architecture suffers from poor utilization of hardware resources mainly due to the dynamic workloads between different phases in GNN. To address these issues, existing GNN accelerators adopt a unified structure with numerous processing elements and high bandwidth memory. However, the large amount of data movement between the processor and memory could heavily downgrade the performance of such accelerators in real-world graphs. As a result, the processing-in-memory architecture, such as the ReRAM-based crossbar, becomes a promising solution to reduce the memory overhead of GNN training. In this work, we present the TCAM-GNN, a novel TCAM-based data processing strategy, to enable high-throughput and energy-efficient GNN training over ReRAM-based crossbar architecture. Several hardware co-designed data structures and placement methods are proposed to fully exploit the parallelism in GNN during training. In addition, we propose a dynamic fixed-point formatting approach to resolve the precision issue. An adaptive data reusing policy is also proposed to enhance the data locality of graph features by the bootstrapping batch sampling approach. Overall, TCAM-GNN could enhance computing performance by 4.25× and energy efficiency by 9.11× on average compared to the neural network accelerators.

Fund transfer fraud detection: Analyzing irregular transactions and customer relationships with self-attention and graph neural networks

In the era of digital transformation, personalized recommendation systems play a critical role in mitigating information overload by guiding users toward relevant content, products, and services. Traditional approaches such as Collaborative Filtering and Content-Based Filtering, while widely adopted, struggle with cold-start issues, data sparsity, and the inability to capture complex relationships within heterogeneous data. Recent advances in Graph Neural Networks (GNNs) present a promising paradigm, as user–item interactions, social connections, and knowledge graphs naturally exhibit graph structures. However, despite growing interest, there remains a lack of systematic reviews focusing specifically on the application of GNNs to personalized recommendation systems. This survey addresses that gap by analyzing recent studies from 2020 to 2025, classifying GNN architectures (e.g., GCN, GAT, GraphSAGE, LightGCN, and specialized variants), and mapping their application across collaborative, content-based, and hybrid recommendation strategies. The findings highlight GNNs’ superior ability to address cold-start and sparsity challenges, enhance personalization, and improve interpretability through integration with knowledge graphs. By consolidating current advancements and open challenges, this study contributes a comprehensive reference that bridges theoretical development with practical needs, while outlining future directions for more scalable, explainable, and ethical recommender systems.

In an era of information explosion, recommender systems are vital tools to deliver personalized recommendations for users. The key of recommender systems is to forecast users' future behaviors based on previous user-item interactions. Due to their strong expressive power of capturing high-order connectivities in user-item interaction data, recent years have witnessed a rising interest in leveraging Graph Neural Networks (GNNs) to boost the prediction performance of recommender systems. Nonetheless, classic Matrix Factorization (MF) and Deep Neural Network (DNN) approaches still play an important role in real-world large-scale recommender systems due to their scalability advantages. Despite the existence of GNN-acceleration solutions, it remains an open question whether GNN-based recommender systems can scale as efficiently as classic MF and DNN methods. In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy. Extensive experiments and ablation studies are presented to validate the effectiveness and scalability of the proposed algorithm. Our implementation based on PyTorch is available.

The application of recommendation technologies has been crucial in the promotion of physical and digital content across numerous global platforms such as Amazon, Apple, and Netflix. Our study aims to investigate the advantages of employing recommendation technologies on educational platforms, with a particular focus on an educational platform for learning and practicing music. Our research is based on data from Tomplay, a music platform that offers sheet music with professional audio recordings, enabling users to discover and practice music content at varying levels of difficulty. Through our analysis, we emphasize the distinct interaction patterns on educational platforms like Tomplay, which we compare with other commonly used recommendation datasets. We find that interactions are comparatively sparse on educational platforms, with users often focusing on specific content as they learn, rather than interacting with a broader range of material. Therefore, our primary goal is to address the issue of data sparsity. We achieve this through entity resolution principles and propose a neural network (NN)-based recommendation model. Further, we improve this model by utilizing graph neural networks (GNNs), which provide superior predictive accuracy compared to NNs. Notably, our study demonstrates that GNNs are highly effective even for users with little or no historical preferences (cold-start problem). Our cold-start experiments also provide valuable insights into an independent issue, namely, the number of historical interactions needed by a recommendation model to gain a comprehensive understanding of a user. Our findings demonstrate that a platform acquires a solid knowledge of a user’s general preferences and characteristics with 50 past interactions. Overall, our study makes significant contributions to information systems research on business analytics and prescriptive analytics. Moreover, our framework and evaluation results offer implications for various stakeholders, including online educational institutions, education policymakers, and learning platform users.

Recommendation systems is the core of most online experiences, guiding people to the right products, films, music, courses, and even social links when the choices are overwhelming. They work by learning from large interaction logs and applying predictive models to surface content that fits each user’s tastes, steadily improving as algorithms and data grow richer. As AI and deep learning have developed, classic strategies like collaborative filtering and content-based filtering are increasingly paired with, or superseded by, neural architectures that can model more nuanced patterns in behaviour and content. Among these neural approaches, graph neural networks—and especially Graph Attention Networks (GATs)—have become influential for recommendation because they treat users and items as nodes in a graph and learn from the connections between them. With attention mechanisms, GATs decide which neighbours matter most for a given prediction, amplifying useful signals and dampening noise to learn stronger user and item representations. This survey traces how the industry moved from traditional methods to graph-based models centred on GATs, comparing approaches on scalability, ranking accuracy, data sparsity, and interpretability across widely used benchmarks. Drawing from recent peer‑reviewed work, it highlights architectures and training practices that consistently help in real-world settings, as well as gaps that still limit robust deployment at scale. Looking forward, several directions stand out: using explainable AI to clarify why specific items are recommended, combining reinforcement learning with GATs for adaptive policies, and adopting federated learning to protect user privacy while training on distributed data. The versatility of GAT-based recommenders is already visible across domains—from e‑commerce and online learning to healthcare and social feeds—where graph structure and selective attention naturally fit the data. Overall, the evidence points to GATs as a key ingredient for the next generation of personalized, context‑aware, and trustworthy recommendation systems. Keywords: Recommendation Systems, Collaborative Filtering, Graph Neural Networks, Graph Attention Networks

For some session recommendation algorithms, only the information in the target session is modeled, ignoring the auxiliary role of the interactive nearest neighbor sessions to the target session, resulting in the potential collaborative information is not fully utilized. Therefore,we propose a novel recommendation model based on interactive nearest neighbor sessions(ARMBINNS). Firstly,a directed current session graph (DCSG) is constructed, which focuses on the conversion transitions between frequent items in the target session. The directed current session graph is modeled by graph neural network and soft attention mechanism to generate the session representation of user preference items. Then we search the interactive nearest neighbor sessions of the target session, select items from interactive nearest neighbor sessions and construct undirected interactive nearest neighbor graph (UING) with the target session. Similarly, the undirected interactive nearest neighbor graph is modeled by graph neural network and soft attention mechanism to generate a session representation with nearest neighbor information. Finally, rich session embedding is generated by combining the two types of session representation information through the fusion gating mechanism. Through experiments, it is verified that the proposed model has better recommendation performance compared with 9 advanced recommendation methods.

Graph Neural Networks (GNNs) have achieved remarkable success in recent years due to their powerful ability to model non-Euclidean data structures and complex relationships. However, as graph sizes and model complexities continue to grow, the efficient deployment of GNNs across various hardware platforms presents significant challenges. The two main computation modes in GNN inference exhibit distinct characteristics in sparsity and computational density, which results in imbalanced workload distribution and inefficient utilization of compute and memory bandwidth. Furthermore, subgraph partitioning strategies, commonly adopted to address on-chip resource constraints, frequently introduce write-back overhead and port conflicts, thereby limiting overall system throughput. To address these challenges, we propose TernaryGNNs, a high-throughput, area-efficient ternary weight GNN inference framework targeting CPU-FPGA heterogeneous platforms. First, we introduce a precision-preserving ternary quantization method that maintains model accuracy with 1.016% degradation, while achieving an average weight sparsity of 81.1% and a parameter reduction rate of 94.71%. Next, by exploiting sparsity, we reformulate GNN inference as Sparse Matrix–Dense Matrix Multiplication (SpMM) or Sparse General Matrix–Matrix Multiplication (SpGEMM) computation and propose a unified sparse-optimized processor architecture. Finally, we present a comprehensive software–hardware co-design framework that ensures adaptability to the evolving landscape of diverse GNN model architectures. Our framework supports nine mainstream GNN models. Compared to the State-of-the-Art (SOTA) general-purpose GNN processor GraphOPU, TernaryGNNs achieves an average \(2.79\times\) hardware performance improvement, \(1.70\times\) end-to-end performance improvement, and \(2.83\times\) area-efficiency improvement. Compared to the leading overlay accelerator FP-GNN, it delivers \(6.73\times\) hardware performance improvement on average.

This paper presents a new Intelligent Anti-Money Laundering Transaction Pattern Recognition System based on Graph Neural Networks (GNNs). The proposed method addresses the limitations of anti-money laundering (AML) by using graphical representation and deep learning techniques. We introduce general methods for creating financial markets that are integrated according to different shapes, including structural and physical. A custom GNN architecture is developed, featuring heterogeneous graph convolution, listening mechanisms, and physical models to capture the exchange patterns. The analysis of the world’s big data shows that the best performance of our method achieved a 35.2% Money Laundering Detection Rate (MLDR) in the top 1% of the flag business, do the best way.