Unveiling Defect Motifs in Amorphous GeSe Using Machine Learning Interatomic Potentials.

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.

This study introduces a novel approach to drug discovery in regenerative medicine through the utilization of a graph neural network (GNN). The research methodology integrates the development and training of the GNN with a subsequent evaluation of its performance metrics. The first phase involves the generation of synthetic data simulating a biological network, employing networkX and NumPy libraries to construct a random graph with Erdos-Renyi topology. The data, representing cellular responses to biomaterials, is then converted into PyTorch tensors for compatibility with the GNN architecture. The GNN model, characterized by two fully connected layers with ReLU and log-softmax activations, captures intricate relationships within the graph-structured data. The second phase employs a stochastic gradient descent algorithm, specifically the Adam optimizer, to train the GNN over 100 epochs using the cross-entropy loss for multi-class classification. The research methodology extends to the evaluation phase, producing three distinct output graphs for analysis: Visualization of the graph structure, a comparison between predicted and true labels, and a plot illustrating training loss over epochs. Performance metrics, including accuracy, precision, recall, and F1-score, are computed to assess the model’s predictive capabilities quantitatively. The study concludes with a discussion on the nuances revealed by each graph and their implications for refining GNN models in the context of drug discovery for regenerative medicine.

This study presents a novel approach that synergizes community detection algorithms with various Graph Neural Network (GNN) models to bolster link prediction in scientific literature networks. By integrating the Louvain community detection algorithm into our GNN frameworks, we consistently enhanced the performance across all models tested. For example, integrating the Louvain model with the GAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifying the typical improvements observed. Similar gains were noted when the Louvain model was paired with other GNN architectures, confirming the robustness and effectiveness of incorporating community-level insights. This consistent increase in performance—reflected in our extensive experimentation on bipartite graphs of scientific collaborations and citations—highlights the synergistic potential of combining community detection with GNNs to overcome common link prediction challenges such as scalability and resolution limits. Our findings advocate for the integration of community structures as a significant step forward in the predictive accuracy of network science models, offering a comprehensive understanding of scientific collaboration patterns through the lens of advanced machine learning techniques.

The rapid advancements in machine learning have opened up new possibilities for solving complex problems, including in highly specialized applications with notable impact on relevant diseases, such as cancer. A critical aspect of cancer treatment is histopathological image analysis, a field that analyzes large zoomable images at a microscope level, to understand how the disease affected the patient, enabling patient-tailored treatment strategies. However, progress in this area relies heavily on interdisciplinary collaboration and the development of methods that utilize highquality annotated datasets effectively. In this thesis, we address these challenges by proposing a new collaborative annotation software for Whole Slides Images. Using the software, we aid in the construction of novel annotated datasets with application-specific goals. Then, inspired by the pathologist\'s work methodology, we develop a novel Graph Neural Network (GNN) technique based on activation maps that models neighborhood representation based on the presence or absence of features in the neighborhood. Our approach is based on the Message Passing architecture, which although very popular, may limit graph representation by suffering from issues such as limited injectability and oversquashing, depending on the GNN architecture and task. Moreover, increasing traditional GNN\'s receptive field requires deepening the neural network, which introduces additional challenges, such as higher computational requirements. In contrast, our approach projects the graph\'s features to a fixed-size map representation with Self-Organizing Maps, which are activated based on the presence and distance of features from the central node, within the model\'s configurable receptive field. Lastly, the activation map keeps the graph\'s features within their original domain during aggregation, which has benefits for interpretability. We conclude this work by training the proposed GNN on a novel annotated dataset developed with the proposed tool, and using its interpretability advantages to highlight the patterns it identifies, contrasting it with a pathologist\'s expectations. This work contributes to the advancement of histopathological image analysis by proposing novel research tools, annotated data, and methods, paving the way for more accurate and reliable AI-based personalized medicine.

Accurate modeling of aqueous metal salt solutions is essential for understanding processes relevant to environmental safety, energy storage, and separation technologies. Trace metals such as As3+ at low concentrations pose significant health and environmental risks. They are challenging to simulate due to limitations in both classical force fields (CFFs), which lack accuracy, and ab initio methods, which are restricted to short trajectories. In this study, we develop machine-learned interatomic potentials (MLIPs) to model aqueous AsCl3 and MgCl2 using the NequIP/Allegro equivariant graph neural network architecture trained on ab initio molecular dynamics (AIMD) and density functional theory data. Our MLIP models accurately reproduce ab initio energies and forces while capturing solvation structure, ion diffusion, and hydration dynamics more effectively than CFFs (AMBER and UFF models). Our MLIPs achieve energy MAEs < 1 meV/atom and force RMSEs < 40 meV/Å, while providing an O(104) speedup over AIMD. These MLIPs offer a reliable and efficient alternative for modeling trace metal speciation and transport, with implications for improved separation and environmental processes.

Machine learning interatomic potentials have become an indispensable tool for materials science, enabling the study of larger systems and longer timescales. State-of-the-art models are generally graph neural networks that employ message passing to iteratively update atomic embeddings that are ultimately used for predicting properties. In this work we extend the message passing formalism with the inclusion of a continuous variable that accounts for fractional atomic existence. This allows us to calculate the gradient of the Gibbs free energy with respect to both the Cartesian coordinates of atoms and their existence. Using this we propose a gradient-based grand canonical optimization method and document its capabilities for a Cu(110) surface oxide.

In this paper we survey our recent results characterizing various graph neural network (GNN) architectures in terms of their ability to classify nodes over graphs, for classifiers based on unary logical formulas- or queries. We focus on the language FOC2, a well-studied fragment of FO. This choice is motivated by the fact that FOC2 is related to theWeisfeiler-Lehman (WL) test for checking graph isomorphism, which has the same ability as GNNs for distinguishing nodes on graphs. We unveil the exact relationship between FOC2 and GNNs in terms of node classification. To tackle this problem, we start by studying a popular basic class of GNNs, which we call AC-GNNs, in which the features of each node in a graph are updated, in successive layers, according only to the features of its neighbors. We prove that the unary FOC2 formulas that can be captured by an AC-GNN are exactly those that can be expressed in its guarded fragment, which in turn corresponds to graded modal logic. This result implies in particular that ACGNNs are too weak to capture all FOC2 formulas. We then seek for what needs to be added to AC-GNNs for capturing all FOC2. We show that it suffices to add readouts layers, which allow updating the node features not only in terms of its neighbors, but also in terms of a global attribute vector. We call GNNs with readouts ACR-GNNs. We also describe experiments that validate our findings by showing that, on synthetic data conforming to FOC2 but not to graded modal logic, AC-GNNs struggle to fit in while ACR-GNNs can generalise even to graphs of sizes not seen during training.

Graph Neural Networks (GNNs), which generalize deep neural networks to graph-structured data, have drawn considerable attention and achieved state-of-the-art performance in numerous graph related tasks. However, existing GNN models mainly focus on designing graph convolution operations. The graph pooling (or downsampling) operations, that play an important role in learning hierarchical representations, are usually overlooked. In this paper, we proposed a novel multi-view graph pooling operator dubbed as MVPool, which ranks nodes across different views with different contextual graph information. Meanwhile, attention mechanism is utilized to promote the collaboration of different views for generating robust node rankings. Then the pooling operation adaptively selects a subset of nodes to form an induced subgraph based on the ranking list. To preserve the underlying graph topological information, we further introduce a structure learning mechanism to learn a refined graph structure for the pooled graph at each layer. The proposed MVPool operator is a general strategy that can be integrated into various graph neural network architectures. By combining MVPool operator with graph neural networks, we perform hierarchical representation learning for both node and graph level classification as well as clustering tasks. Experimental results on nine widely used benchmarks demonstrate the effectiveness of our proposed model.

The inherent complexity and heterogeneity of the Internet of Things (IoT) ecosystem present significant challenges for developing effective intrusion detection systems. While graph deep-learning-based methods have shown promise in cybersecurity applications, existing approaches primarily construct graphs based on physical network connections, which may not effectively capture node representations. This paper proposes a Top-K Similarity Graph Framework (TKSGF) for IoT network intrusion detection. Instead of relying on physical links, the TKSGF constructs graphs based on Top-K attribute similarity, ensuring a more meaningful representation of node relationships. We employ GraphSAGE as the Graph Neural Network (GNN) model to effectively capture node representations while maintaining scalability. Furthermore, we conducted extensive experiments to analyze the impact of graph directionality (directed vs. undirected), different K values, and various GNN architectures and configurations on detection performance. Evaluations on binary and multi-class classification tasks using the NF-ToN IoT and NF-BoT IoT datasets from the Machine-Learning-Based Network Intrusion Detection System (NIDS) benchmark demonstrated that our proposed framework consistently outperformed traditional machine learning methods and existing graph-based approaches, achieving superior classification accuracy and robustness.

This paper compares the performance of two graph neural network architectures on the emulation of a cardiac mechanic model of the left ventricle of the heart. These models can be applied directly on the same computational mesh of the left ventricle geometry that is used by the expensive numerical forward solver, precluding the need for a low-order approximation of the true geometry. Our results show that these emulation approaches incur negligible loss in accuracy compared in the forward simulator, while making predictions multiple orders of magnitude more quickly, raising the prospect for their use in both forward and inverse problems in cardiac modelling.

Theoretical models of galaxy formation and evolution are primarily investigated through cosmological simulations and semi-analytical models. The former method consumes O(106) core-hours explicitly modeling the dynamics of the galaxies, whereas the latter method only requires O(103) core-hours foregoing directly simulating internal structure for computational efficiency. In this work, we present a proof-of-concept machine learning regression model, using a graph neural network architecture, to predict the stellar mass of high-redshift galaxies solely from their dark matter merger trees, trained from a radiation hydrodynamics cosmological simulation of the first galaxies.

Graph Neural Networks have been popularly investigated and achieved promising performance in node-wise and graph-level tasks, like node classification and graph classification. For graph classification, correctly defining pooling operations to coarsen an input graph for distilling hierarchical knowledge from node representations is demanded. Some works have devised pooling strategies to summarize a graph by evaluating and gathering the ranked top-k representative nodes. Yet there is few literature to explicitly consider the node's degree-specific structure information in pooling procedure. One intuition is the larger the node's degree is, the more important it probably is in the entire graph. In this work, we propose a novel Degree-Induced Pooling (DIPool), which can be integrated into various graph neural network architectures. Specifically, the DIPool layer devises two approaches for explicitly incorporating the characteristics and degree-specific structures of nodes into a unified criterion to evaluate the importance of the nodes within an input graph. This setting permits to retain more representative nodes to generate the newly pooled graph. Experimental results on a collection of public benchmarks have demonstrated the effectiveness of the proposed DIPool operator. Especially, DIPool achieves relative improvements of 3.69% on NCI1 and 3.24% on NCI109 compared with the best baseline ASAP.

Accurate and efficient simulation of photoinduced dynamics in materials remains a significant challenge due to the computational cost of excited-state electronic structure calculations and the necessity to account for excitonic effects. In this work, we present a machine learning (ML)-accelerated approach to nonadiabatic molecular dynamics simulations that incorporates excitonic effects by predicting excited-state wave functions via configuration interaction coefficients and excitation energies using a graph neural network (GNN) architecture. The GNN model leverages molecular orbital information from ground-state calculations to construct input graphs, enabling efficient and accurate prediction of relevant excited-state wave functions and energies required for ab initio-based fewest-switches surface hopping simulations. Benchmarking on a zinc phthalocyanine-fullerene (ZnPc-C60) donor-acceptor system reveals that these ML-predicted properties agree closely with those obtained from linear-response time-dependent density functional theory calculations while boosting the computational efficiency significantly. The ML-accelerated simulations reproduce excited-state dynamics with high fidelity, demonstrating the methodological capability to study complex photodynamical processes in large systems. This work provides a general and scalable framework for efficient excited-state dynamics simulations in materials where excitonic effects play a vital role.

Polypharmacy, the simultaneous use of multiple medications, significantly increases the risk of adverse Drug-Drug Interactions (DDIs), posing serious challenges to patient safety and healthcare systems. Traditional DDI detection methods are often binary and lack clinical interpretability, failing to provide actionable risk assessments for healthcare professionals. This survey comprehensively reviews computational approaches for DDI prediction, with a focus on Graph Neural Network (GNN) architectures and their integration with Large Language Models (LLMs) for enhanced clinical decision support. We analyze ten representative works spanning relational graph convolutional networks, meta path based heterogeneous networks, multimodal fusion frameworks, and hybrid approaches. Our analysis reveals that while GNN based methods show superior performance in capturing molecular relationships, significant gaps remain in clinical interpretability, risk level classification, and real world deployment. Building on these insights, we propose an integrated framework combining GNNs for molecular analysis with LLMs for contextual reasoning and recommendation refinement. The proposed system categorizes DDI risks into low, moderate, and high levels and suggests safer alternative drugs. We discuss the societal relevance of DDI prediction systems in promoting sustainable healthcare and their alignment with Sustainable Development Goals (SDGs). Finally, we outline future research directions including real time clinical integration, multimodal data fusion, and enhanced explainability for non-technical users.

Machine learning interatomic potentials (MLIPs) enables molecular dynamics (MD) simulations with ab initio accuracy and has been applied to various fields of physical science. However, the performance and transferability of MLIPs are limited by insufficient labeled training data, which require expensive ab initio calculations to obtain the labels, especially for complex molecular systems. To address this challenge, we design a novel geometric structure learning paradigm that consists of two stages. We first generate a large quantity of 3D configurations of target molecular system with classical molecular dynamics simulations. Then, we propose geometry-enhanced self-supervised learning consisting of masking, denoising, and contrastive learning to better capture the topology and 3D 1 geometric information from the unlabeled 3D configurations. We evaluate our method on various benchmarks ranging from small molecule datasets to complex periodic molecular systems with more types of elements. The experimental results show that the proposed pre-training method can greatly enhance the accuracy of MLIPs with few extra computational costs and works well with different invariant or equivariant graph neural network architectures. Our method improves the generalization capability of MLIPs and helps to realize accurate MD simulations for complex molecular systems.