Introduction to Graph Neural Network

Graph neural networks (GNNs) is an information - processing system that uses message passing among graph nodes. In recent years, GNN variants including graph attention network (GAT), graph convolutional network (GCN), and graph recurrent network (GRN) have shown revolutionary performance in computer vision applications using deep learning and artificial intelligence. These neural network model extensions, collect information in the form of graphs. GNN may be divided into three groups based on the challenges it solves: link prediction, node classification, graph classification. Machines can differentiate and recognise objects in image and video using standard CNNs. Extensive amount of research work needs to be done before robots can have same visual intuition as humans. GNN architectures, on the other hand, may be used to solve various image categorization and video challenges. The number of GNN applications in computer vision not limited, continues to expand. Human-object interaction, actin understanding, image categorization from a few shots and many more. In this paper use of GNN in image and video understanding, design aspects, architecture, applications and implementation challenges towards computer vision is described. GNN is a strong tool for analysing graph data and is still a relatively active area that needs further researches attention to solve many computer vision applications.

With the ubiquity of complex networks in domains as diverse as social network analysis, recommender systems and epidemiology, improvements in link predictions have a potential for far-reaching impact. In machine learning, a well-known approach to improve classification performance is to combine several methods in an ensemble. It is also well established that, diversity or complementarity of the classifiers to be combined, is a prerequisite for a potential performance improvement of the formed ensemble. In this work, we combine link prediction heuristics (e.g. Common Neighbour, Adamic-Adar etc.), with static graph neural networks, discrete dynamic graph neural networks, and continuous dynamic graph neural networks. We analyze the importance of each of the methods and how complementary they are with respect to each other. We also use greedy searches to select better subsets of methods to combine and train the ensemble in a roll-forward manner to make it adapt to changes in the dynamic network over time. In the conducted experiments on a number of challenging link prediction tasks, the ensemble from the greedy search and the roll-forward ensemble shows on average a 55% and 61% improvement respectively, over the best single method.

Deep learning has led to major advances in fields like natural language processing, computer vision, and other Euclidean data domains. Yet, many important fields have data defined on irregular domains, requiring graphs to be explicitly modeled. One such application is drug discovery. Recently, research has found that using graph neural network (GNN) models, given enough data, can perform better than using human-engineered fingerprints or descriptors in predicting molecular properties of potential antibiotics.We explore these state-of-the-art AI models on predicting desirable molecular properties for drugs that can inhibit SARS-CoV-2. We build upon the GNN models with ideas from recent breakthroughs in geometric deep learning, inspired by the topologies of the molecules. In this poster paper, we present an overview of the drug discovery framework, drug-target interaction framework, and GNNs. Preliminary results on two COVID-19 related datasets are encouraging, achieving a ROC-AUC of 0.72 for FDA-approved chemical library screened against SARS-CoV-2 in vitro.

Recent studies have shown that the problems of cold processing and data sparsity in recommender systems can be well alleviated with the help of knowledge graph information. Meanwhile, since the information in recommender systems can be represented by graph data structure, graph neural network has great advantages in recommendatory system. Therefore, graph neural network can better mine the deep relationship between objects in the recommender systems which combines with information from knowledge graph. This paper reviews the application of graph neural network in knowledge graph aided recommendation systems. Specifically, this paper firstly sorts out the related knowledge of knowledge graph, recommendation system and graph neural network, including the cold processing and data sparsity, the structure of knowledge graph, and the basic modules of graph neural network. This paper also summarizes the methods such as KGAT and CKAN used in knowledge graph aided recommendation systems in recent years, and gives some discussion on the development of this field.

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.

A survey of graph neural network based recommendation in social networks

AI-Driven molecule generation and bioactivity prediction: A multi-model approach combining VAE, graph and language-based neural networks.

Recent advances in Graph Neural Networks (GNNs) have changed the landscape of modern graph analytics. The complexity of GNN training and the scalability challenges have also sparked interest from the systems community, with efforts to build systems that provide higher efficiency and schemes to reduce costs. However, we observe that many such systems basically "reinvent the wheel" of much work done in the database world on scalable graph analytics engines. Further, they often tightly couple the scalability treatments of graph data processing with that of GNN training, resulting in entangled complex problems and systems that often do not scale well on one of those axes. In this paper, we ask a fundamental question: How far can we push existing systems for scalable graph analytics and deep learning (DL) instead of building custom GNN systems? Are compromises inevitable on scalability and/or runtimes? We propose Lotan, the first scalable and optimized data system for full-batch GNN training with decoupled scaling that bridges the hitherto siloed worlds of graph analytics systems and DL systems. Lotan offers a series of technical innovations, including re-imagining GNN training as query plan-like dataflows, execution plan rewriting, optimized data movement between systems, a GNN-centric graph partitioning scheme, and the first known GNN model batching scheme. We prototyped Lotan on top of GraphX and PyTorch. An empirical evaluation using several real-world benchmark GNN workloads reveals a promising nuanced picture: Lotan significantly surpasses the scalability of state-of-the-art custom GNN systems, while often matching or being only slightly behind on time-to-accuracy metrics in some cases. We also show the impact of our system optimizations. Overall, our work shows that the GNN world can indeed benefit from building on top of scalable graph analytics engines. Lotan's new level of scalability can also empower new ML-oriented research on ever-larger graphs and GNNs.

To meet the needs of AI design in analog IC design automation and especially in big data applications, the application of sensitive and precise Graph Neural Network (GNN) recognition will become increasingly necessary. This sensitive GNN recognition is needed to accommodate the highly stringent trade-offs on analog IC design requirements, combined with the increasingly large learning data requirements. Furthermore, more precise GNN recognition will be a fundamental requirement for a more sensitive system to accommodate noise in floating point (FP) calculations, namely inaccuracies and imprecision in IEEE 754 FP calculations. In this study, by refining a previously proposed method that uses the output vector representation (OVR) of the untrained Graph Neural Network (GNN), and by exploiting the numerical reproducibility error in FP calculations, a method for measuring the sensitivity and precision of GNNs for use in analog IC design recognition has been proposed. The results of the sensitivity and precision measurements of the proposed method show a complex combination of effects between dataset quality (the presence or absence of data duplication), the sensitivity of the GNN to distinguish each feature in the dataset, the complexity of the calculations that occur in the GNN, and the level of quality of the FP calculations performed by the processing unit related to the non-ideal FP calculations. With certain GNN configurations, the proposed method also succeeded in measuring the difference in FP calculation quality of Central Processing Unit (CPU) and Graphics Processing Unit (GPU), where, for big data applications, from the tests carried out, the maximum amount of data that can be distinguished by the CPU is 25 to 100 times more than with the GPU. Because it only uses untrained GNN OVR and does not involve any training process in obtaining results, the proposed method is still unable to obtain a correlation with the final value of GNN performance after training is complete. The measurement method using GNN OVR involving the learning process is future work.

Graph neural networks (GNNs) have made rapid developments in the recent years. Due to their great ability in modeling graph-structured data, GNNs are vastly used in various applications, including high-stakes scenarios such as financial analysis, traffic predictions, and drug discovery. Despite their great potential in benefiting humans in the real world, recent study shows that GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data and lack interpretability, which have risk of causing unintentional harm to the users and society. For example, existing works demonstrate that attackers can fool the GNNs to give the outcome they desire with unnoticeable perturbation on training graph. GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias. Consequently, trust-worthy GNNs in various aspects are emerging to prevent the harm from GNN models and increase the users’ trust in GNNs. In this paper, we give a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability. For each aspect, we give the taxonomy of the related methods and formulate the general frameworks for the multiple categories of trustworthy GNNs. We also discuss the future research directions of each aspect and connections between these aspects to help achieve trustworthiness.

PurposeDrug-induced liver injury (DILI) is a significant concern in drug development, often leading to the discontinuation of clinical trials and the withdrawal of drugs from the market. This study explores the application of graph neural networks (GNNs) for DILI prediction, using molecular graph representations as the primary input.MethodsWe evaluated several GNN architectures, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), Graph Sample and Aggregation (GraphSAGE), and Graph Isomorphism Networks (GINs), using the latest FDA DILI dataset and other molecular property prediction datasets. We introduce a novel approach that creates a custom graph dataset, driven by molecular optimisation, that incorporates detailed and realistic chemical features such as bond lengths and partial charges as input into the GNN models. We have named our model approach DILIGeNN.ResultsDILIGeNN achieved an AUC of 0.897 on the DILI dataset, surpassing the current state-of-the-art model in the DILI prediction task. Furthermore, DILIGeNN outperformed the state-of-the-art in other graph-based molecular prediction tasks, achieving an AUC of 0.918 on the Clintox dataset, 0.993 on the BBBP dataset, and 0.953 on the BACE dataset, indicating strong generalisation and performance across different datasets.ConclusionDILIGeNN, utilising a single graph representation as input, outperforms the state-of-the-art methods in DILI prediction that incorporate both molecular fingerprint and graph-structured data. These findings highlight the effectiveness of our molecular graph generation and the GNN training approach as a powerful tool for early-stage drug development and drug repurposing pipeline.Scientific Contribution: DILIGeNN is a GNN framework that extracts graph features from 3D optimised molecular structures as is done in target-based drug discovery and molecular docking simulation. Our method is the first to encode spatial and electrostatic information into a single graph representation, as opposed to other work that require multiple graphs or additional chemical descriptors for feature representation. Our approach, using warm starts following repeated early stopping during training, outperforms the current state-of-the-art methods in liver toxicity (DILI), permeability (BBBP) and activity (BACE) prediction tasks.Graphic

The n-octanol/buffer solution distribution coefficient at pH = 7.4 (log D7.4) is an indicator of lipophilicity, and it influences a wide variety of absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties and druggability of compounds. In log D7.4 prediction, graph neural networks (GNNs) can uncover subtle structure-property relationships (SPRs) by automatically extracting features from molecular graphs that facilitate the learning of SPRs, but their performances are often limited by the small size of available datasets. Herein, we present a transfer learning strategy called pretraining on computational data and then fine-tuning on experimental data (PCFE) to fully exploit the predictive potential of GNNs. PCFE works by pretraining a GNN model on 1.71 million computational log D data (low-fidelity data) and then fine-tuning it on 19,155 experimental log D7.4 data (high-fidelity data). The experiments for three GNN architectures (graph convolutional network (GCN), graph attention network (GAT), and Attentive FP) demonstrated the effectiveness of PCFE in improving GNNs for log D7.4 predictions. Moreover, the optimal PCFE-trained GNN model (cx-Attentive FP, Rtest2 = 0.909) outperformed four excellent descriptor-based models (random forest (RF), gradient boosting (GB), support vector machine (SVM), and extreme gradient boosting (XGBoost)). The robustness of the cx-Attentive FP model was also confirmed by evaluating the models with different training data sizes and dataset splitting strategies. Therefore, we developed a webserver and defined the applicability domain for this model. The webserver (http://tools.scbdd.com/chemlogd/) provides free log D7.4 prediction services. In addition, the important descriptors for log D7.4 were detected by the Shapley additive explanations (SHAP) method, and the most relevant substructures of log D7.4 were identified by the attention mechanism. Finally, the matched molecular pair analysis (MMPA) was performed to summarize the contributions of common chemical substituents to log D7.4, including a variety of hydrocarbon groups, halogen groups, heteroatoms, and polar groups. In conclusion, we believe that the cx-Attentive FP model can serve as a reliable tool to predict log D7.4 and hope that pretraining on low-fidelity data can help GNNs make accurate predictions of other endpoints in drug discovery.

Purpose To develop an explainable radiopathomic graph deep learning (RPGDL) system for multiscale spatial-contextual modeling of intratumoral heterogeneity and evaluate its performance for the prediction of pathologic complete response (pCR) to neoadjuvant therapy in breast cancer. Materials and Methods The RPGDL system was developed from dual-center retrospective analysis of patients with biopsy-proven invasive breast cancer (May 2018-August 2024). For each tumor, individual radiomic and pathomic graphs were generated from pretherapeutic MRI and hematoxylin-eosin-stained biopsy slide images, respectively. These graphs were then processed by three distinct graph neural networks (GNNs): radiomic, pathomic, and radiopathomic. GNN performance was assessed with the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). A multifaceted approach was used to explain the GNNs' predictions. Results The training set included 582 (mean age, 52 years ± 9 [SD]) patients and the external test set 468 (50 years ± 10) patients from centers 1 and 2, respectively. The radiomic GNN achieved AUCs of 0.89 (95% CI: 0.85, 0.93) in the training set and 0.84 (95% CI: 0.80, 0.89) in the external test set; the pathomic GNN achieved AUCs of 0.87 (95% CI: 0.83, 0.91) in the training set and 0.83 (95% CI: 0.78, 0.88) in the external test set, with no significant difference between them (P > .05). The radiopathomic GNN outperformed both single-modality GNNs (training set: AUC, 0.95 [95% CI: 0.92, 0.98]; external test set: AUC, 0.91 [95% CI: 0.87, 0.94]; P < .05; NRI and IDI confirmed). Pathomic graphs dominated probability increases for pCR predictions, while radiomic graphs drove probability decreases for non-pCR predictions. Multifaceted analyses verified GNNs' explainability. Conclusion The developed RPGDL system enabled multiscale spatial-contextual intratumoral heterogeneity modeling for high-performance, explainable prediction of pCR to neoadjuvant therapy in breast cancer. Keywords: Dynamic Contrast-enhanced MRI, Breast, Tumor Response, Radiology-Pathology Integration, Prognosis, Principal Component Analysis, Perception, Supervised Learning, Reconstruction Algorithm Supplemental material is available for this article. © RSNA, 2026.

A recommendation system is a set of programs that utilize different methodologies for relevant item selection for the user. Graph neural networks have been extensively used in recent years to improve the quality of recommendations across all domains. A general recommendation system’s main goal is to recommend items to the user accurately, and it frequently prioritizes items that are well-liked or mainstream. If the model concentrates only on one specific item category from the users’ past preferences, then recommendations for the target user will become too obvious. To address this problem, diversity in the recommendation system is introduced. The model IG-DivRS (Item-Enhanced Graph Neural Network for a Diversified Recommendation System) is proposed. Our proposed model uses a Graph Neural Network (GNN) with the user’s interacted and non-interacted item history for diversified recommendation generation. The novelty of our proposed model is to explore the effect of non-interacted items on the target user for diversified recommendation generation. Instead of selecting random non-interacted items for the target user, we apply the DPP(Determinantal Point Process) algorithm to select the non-interacted item appropriately. The detailed experimental analysis shows that our model ID-DivRS outperforms the state-of-the-art model in accuracy and diversity.

The field of e-commerce provides customers with many kinds of goods to choose from. It is also a challenge for consumers to choose among tens of thousands of product categories. The emergence of recommender systems solves such problems for consumers to a certain extent because it would recommend products that may fulfil their needs for consumers. Finding user preferences or rankings for a specific item can be aided by recommender systems. It uses specialized software and techniques to offer suggestions for items utilized by various users. To increase customer satisfaction or sell different things for e-commerce platforms, recommender systems advise consumers about specific items they may be interested in or desire to utilize. Graph neural networks generalize effectively to new datasets because they can learn the graph structure of various datasets. To put it another way, this makes Graph Neural Networks (GNNs) the perfect recommender systems for various real-world issues. As a result, the growth and usage of neural graph networks in recommender systems and the limitations of graph neural networks will be covered in detail in this paper.