Learning for Graph Matching and Related Combinatorial Optimization Problems

This research develops and evaluates an intelligent system that integrates machine learning (ML) with Robotic Process Automation (RPA) to automate data extraction from Indonesian National ID Cards (KTP). The study provides a comparative analysis of two primary models: a Graph Neural Network (GNN) and a Convolutional Neural Network (CNN), benchmarked against a baseline RPA system without an ML component. The central hypothesis is that integrating advanced ML models into an RPA workflow will yield a highly accurate and efficient solution for document data extraction. Experimental results show a distinct performance hierarchy among the tested methods. The CNN model achieved the highest accuracy at 57.72%. In comparison, the GNN model yielded a lower accuracy of 48.81%. Both ML-driven approaches significantly outperformed the baseline RPA system, which completely failed to produce any valid extractions (0% accuracy). These quantitative findings partially support the initial hypothesis, confirming that an ML component is essential for this task. However, they also reveal that under the tested conditions, the CNN's feature extraction capabilities were more effective than the GNN's for handling the noisy, real-world data from KTP images. The results underscore both the potential and current limitations of GNNs in practical document automation pipelines, indicating that further optimization is required to surpass the performance of established computer vision models.

Purpose The blood–brain barrier (BBB) is a major obstacle in neurological drug development, restricting most drugs from entering the brain. To address this, computational models leveraging Artificial Intelligence (AI) and machine learning (ML) have been explored for predicting BBB permeability. This meta-review explores various computational strategies leveraging AI and ML to improve BBB permeability prediction. Methods 31 publications were included in this review following a search in PubMed Central and in the Journal of Cheminformatics. Models are categorized into three groups: (1) traditional ML models using physiochemical descriptors, (2) graph/image-based models leveraging molecular structure, and (3) encoder-based methods using SMILES representations. Results Traditional ML models achieve greater predictive accuracy due to their reliance on explicitly defined features, whereas deep learning methods, particularly graph neural networks (GNNs), show promise but require large-scale datasets and pretraining. Encoder-based methods underperform compared to traditional ML and GNNs, likely due to inadequate feature extraction. Conclusion Despite advancements, challenges such as dataset biases, model interpretability, and the need for experimental validation remain. Future research should explore multi-modal integration and generative AI to enhance BBB permeability prediction and aid drug discovery.

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized.

By examining the patterns of solutions obtained for various instances, one can gain insights into the structure and behavior of combinatorial optimization (CO) problems and develop efficient algorithms for solving them. Machine learning techniques, especially Graph Neural Networks (GNNs), have shown promise in parametrizing and automating this laborious design process. The inductive bias of GNNs allows for learning solutions to mixed-integer programming (MIP) formulations of constrained CO problems with a relational representation of decision variables and constraints. The trained GNNs can be leveraged with primal heuristics to construct high-quality feasible solutions to CO problems quickly. However, current GNN-based end-to-end learning approaches have limitations for scalable training and generalization on larger-scale instances; therefore, they have been mostly evaluated over small-scale instances. Addressing this issue, our study builds on supervised learning of optimal solutions to the downscaled instances of given large-scale CO problems. We introduce several improvements on a recent GNN model for CO to generalize on instances of a larger scale than those used in training. We also propose a two-stage primal heuristic strategy based on uncertainty-quantification to automatically configure how solution search relies on the predicted decision values. Our models can generalize on 16x upscaled instances of commonly benchmarked five CO problems. Unlike the regressive performance of existing GNN-based CO approaches as the scale of problems increases, the CO pipelines using our models offer an incremental performance improvement relative to CPLEX. The proposed uncertainty-based primal heuristics provide 6-75% better optimality gap values and 45-99% better primal gap values for the 16x upscaled instances and brings immense speedup to obtain high-quality solutions. All these gains are achieved through a computationally efficient modeling approach without sacrificing solution quality.

By examining the patterns of solutions obtained for various instances, one can gain insights into the structure and behavior of combinatorial optimization (CO) problems and develop efficient algorithms for solving them. Machine learning techniques, especially Graph Neural Networks (GNNs), have shown promise in parametrizing and automating this laborious design process. The inductive bias of GNNs allows for learning solutions to mixed-integer programming (MIP) formulations of constrained CO problems with a relational representation of decision variables and constraints. The trained GNNs can be leveraged with primal heuristics to construct high-quality feasible solutions to CO problems quickly. However, current GNN-based end-to-end learning approaches have limitations for scalable training and generalization on larger-scale instances; therefore, they have been mostly evaluated over small-scale instances. Addressing this issue, our study builds on supervised learning of optimal solutions to the downscaled instances of given large-scale CO problems. We introduce several improvements on a recent GNN model for CO to generalize on instances of a larger scale than those used in training. We also propose a two-stage primal heuristic strategy based on uncertainty-quantification to automatically configure how solution search relies on the predicted decision values. Our models can generalize on 16x upscaled instances of commonly benchmarked five CO problems. Unlike the regressive performance of existing GNN-based CO approaches as the scale of problems increases, the CO pipelines using our models offer an incremental performance improvement relative to CPLEX. The proposed uncertainty-based primal heuristics provide 6-75% better optimality gap values and 45-99% better primal gap values for the 16x upscaled instances and brings immense speedup to obtain high-quality solutions. All these gains are achieved through a computationally efficient modeling approach without sacrificing solution quality.

The accurate identification of internal and external pressures in thick-walled hyperelastic vessels is a challenging inverse problem with significant implications for structural health monitoring, biomedical devices, and soft robotics. Conventional analytical and numerical approaches address the forward problem effectively but offer limited means for recovering unknown load conditions from observable deformations. In this study, we introduce a Graph-FEM/ML framework that couples high-fidelity finite element simulations with machine learning models to infer normalized internal and external pressures from measurable boundary deformations. A dataset of 1386 valid samples was generated through Latin Hypercube Sampling of geometric and loading parameters and simulated using finite element analysis with a Neo-Hookean constitutive model. Two complementary neural architectures were explored: graph neural networks (GNNs), which operate directly on resampled and feature-enriched boundary data, and convolutional neural networks (CNNs), which process image-based representations of undeformed and deformed cross-sections. The GNN models consistently achieved low root-mean-square errors (≈0.021) and stable correlations across training, validation, and test sets, particularly when augmented with displacement and directional features. In contrast, CNN models exhibited limited predictive accuracy: quarter-section inputs regressed toward mean values, while full-ring and filled-section inputs improved after Bayesian optimization but remained inferior to GNNs, with higher RMSEs (0.023–0.030) and modest correlations (R2). To the best of our knowledge, this is the first work to combine boundary deformation observations with graph-based learning for inverse load identification in hyperelastic vessels. The results highlight the advantages of boundary-informed GNNs over CNNs and establish a reproducible dataset and methodology for future investigations. This framework represents an initial step toward a new direction in mechanics-informed machine learning, with the expectation that future research will refine and extend the approach to improve accuracy, robustness, and applicability in broader engineering and biomedical contexts.

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

Mathematics can be formalized to allow a computer to execute proof steps and recognize whether a statement has been proven. Computer systems that automate mathematics are called automated theorem provers (ATP). The system has inference rules, which prescribe how the axioms and conjecture may be handled during a search for a proof. The number of possible choices at each point in the process can become very large. It would be useful to have a system that can predict which choices are better than other ones, so that a proof may be reached earlier. In this study, automated theorem proving is combined with machine learning, a field concerned with learning patterns in data. The machine learning component, a graph neural network, is tasked with learning to predict which choices are useful and which ones are not. This information can be learned from already finished proofs. The overall goal is to improve the performance of the automated theorem proving systems in terms of theorems proven in a particular time period. It is shown that instantiation and rewriting-based proving systems can be integrated with machine learning and that the systems improve on benchmark datasets.

This book presents a comprehensive exploration of structural pattern recognition with a clear understanding of graph representation and manipulation. It explains graph matching techniques, unearthing the core principles of graph similarity measures, subgraph isomorphism, and advanced algorithms tailored to various pattern recognition tasks. It bridges the gap between theory and application by providing case studies, hands-on examples, and applications. It is a reference book for academicians, researchers, and students working in the fields of structural pattern recognition, computer vision, artificial intelligence, and data science. • Begins with the fundamentals of graph theory, graph matching algorithms, and structural pattern recognition concepts and explains the principles, methodologies, and practical implementations • Presents relevant case studies and hands-on examples across chapters to guide making informed decisions by graph matching • Discusses various graph-matching algorithms, including exact and approximate methods, geometric methods, spectral techniques, graph kernels, and graph neural networks, including practical examples to illustrate the strengths and limitations of each approach • Showcases the versatility of graph matching in real-world applications, such as image analysis, biological molecule identification, object recognition, social network clustering, and recommendation systems • Describes deep learning models for graph matching, including graph convolutional networks (GCNs) and graph neural networks (GNNs)

Chemical heuristics have been fundamental to the advancement of chemistry and materials science. These heuristics are typically established by scientists using knowledge and creativity to extract patterns from limited datasets. Machine learning offers opportunities to perfect this approach using computers and larger datasets. Here, we discuss the relationships between traditional heuristics and machine learning approaches. We show how traditional rules can be challenged by large-scale statistical assessment and how traditional concepts commonly used as features are feeding the machine learning techniques. We stress the waste involved in relearning chemical rules and the challenges in terms of data size requirements for purely data-driven approaches. Our view is that heuristic and machine learning approaches are at their best when they work together.

The procedure of drug-target interaction prediction (DTI) stands as a vital process during drug discovery because it helps reveal which drug substances interact with which biological targets including proteins and receptors. For example, the interactions themselves are too complex to be predictively modelled using single type biological or chemical data; they likewise are so large and varied that approaches traditionally used to predict these interactions are not powerful enough. We use this paper to look at how graph neural networks (GNNs) are used to model molecular structures and predict drug target. GNNs guard their strength in modelling molecular structures because they master the process of detecting atomic and bond relationships thus producing precise molecular representations. The authors evaluate convolutional neural networks (CNNs) and recurrent neural networks (RNNs) alongside GNNs for their use in DTI prediction. The system accepts molecular graphs as its starting data to calculate the predicted interaction probability between drugs and their target proteins. Progressive experimentation has proven the model effectiveness which enables it to reduce drug candidates for experimental verification. The drug discovery process can reach improved efficiency in DTI prediction and accelerate therapeutic development according to results from machine learning (ML) particular GNNs.

The center of human activity and a key point of contact for social interaction between city people and the built environment is the street. With more street-level photos becoming available, urban landscape studies have more chances to examine and evaluate streetscapes closely and from various angles. This manuscript present the graph neural networks (GNN) optimized with gazelle optimization algorithm (GOA) for urban plants cape design based on large-scale street view (UPLS-GNN-GOA). Initially data is taken from ADE20K dataset. Afterward the data is fed to General Robust Subband Adaptive Filtering (GRSAF) based pre-processing process. The pre-processing output is given to Discrete Fractional Fourier Transforms (DFrFT) to extract the street greenery and openness of street canyons. After that, the extracted features are fed to Graph Neural Networks (GNN) to classify the public health, urban microclimate, human perception. The weight parameters of the GNN are optimized using Gazelle Optimization Algorithm (GOA).The UPLS-GNN-GOA method is implemented in Python, and its efficiency is determined using a series of performance evaluation metrics analysis, including accuracy, precision, recall, f1-score, and sensitivity. The proposed UPLS-GNN-GOA method shows the highest accuracy of 98%, precision of 98%, and F1-score of 97% while comparing other existing methods such as urban plantscape design based on convolutional neural network (UPLS-CNN), urban plantscape design based on deep convolutional neural network (UPLS-DCNN) and urban plantscape design based on deep learning and convolutional neural network (UPLS-DL-CNN) respectively.

Extensive studies have been conducted to investigate Artificial Intelligence (AI) in the context of time series data. In this article, we investigate the complex domain of industrial time series, from the dimensions of classical machine learning (ML), deep neural networks (DNNs) and graph neural networks (GNNs). Current surveys often focus on a specific methodology or oversee the connection of diverse approaches; our article bridges this gap by providing an all-inclusive interpretation across numerous techniques. In addition, the aim of this article is to focus on the core areas of time series such as forecasting, classification, and anomaly detection. From traditional methodologies like Autoregressive Integrated Moving Average (ARIMA) and support vector machine (SVM) methods, the advancements of DNNs, for instance long-short-term memory (LSTMs), convolutional neural networks (CNNs), attention mechanisms, and transformers, describe how temporal information is used for forecasting, anomaly detection, and classification. Then the article discusses the advances and limitations in ML, DNN, and GNN in order to improve the different methods in either category. Lastly, we outline future directions and open research questions with the different methodologies used in time series.

Selecting diverse molecules from unexplored areas of chemical space is one of the most important tasks for discovering novel molecules and reactions. This paper proposes a new approach for selecting a subset of diverse molecules from a given molecular list by using two existing techniques studied in machine learning and mathematical optimization: graph neural networks (GNNs) for learning vector representation of molecules and a diverse-selection framework called submodular function maximization. Our method, called SubMo-GNN, first trains a GNN with property prediction tasks, and then the trained GNN transforms molecular graphs into molecular vectors, which capture both properties and structures of molecules. Finally, to obtain a subset of diverse molecules, we define a submodular function, which quantifies the diversity of molecular vectors, and find a subset of molecular vectors with a large submodular function value. This can be done efficiently by using the greedy algorithm, and the diversity of selected molecules measured by the submodular function value is mathematically guaranteed to be at least 63% of that of an optimal selection. We also introduce a new evaluation criterion to measure the diversity of selected molecules based on molecular properties. Computational experiments confirm that our SubMo-GNN successfully selects diverse molecules from the QM9 dataset regarding the property-based criterion, while performing comparably to existing methods regarding standard structure-based criteria. We also demonstrate that SubMo-GNN with a GNN trained on the QM9 dataset can select diverse molecules even from other MoleculeNet datasets whose domains are different from the QM9 dataset. The proposed method enables researchers to obtain diverse sets of molecules for discovering new molecules and novel chemical reactions, and the proposed diversity criterion is useful for discussing the diversity of molecular libraries from a new property-based perspective.

This paper introduces a novel approach for classifying multidimensional physiological and clinical data using Synolitic Graph Neural Networks (SGNNs). SGNNs are particularly good for addressing the challenges posed by high-dimensional datasets, particularly in healthcare, where traditional machine learning and Artificial Intelligence methods often struggle to find global optima due to the “curse of dimensionality”. To apply Geometric Deep Learning we propose a synolitic or ensemble graph representation of the data, a universal method that transforms any multidimensional dataset into a network, utilising only class labels from training data. The paper demonstrates the effectiveness of this approach through two classification tasks: synthetic and fMRI data from cognitive tasks. Convolutional Graph Neural Network architecture is then applied, and the results are compared with established machine learning algorithms. The findings highlight the robustness and interpretability of SGNNs in solving complex, high-dimensional classification problems.