21 papers · ranked by Valyu relevance
Soroush Vahidi
Graph neural networks (GNNs) achieve strong performance on homophilic graphs but often struggle under heterophily, where adjacent nodes frequently belong to different classes. We propose an interpretable and adaptive framework for semi-supervised node classification based on explicit combinatorial inference rather than…
Xueqi Ma, Xingjun Ma, Sarah Erfani, Danilo P. Mandic + 1 more
Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-ofdistribution (OOD) samples is essential for deploying graph neural networks (GNNs) in open-world scenarios. Existing methods typically treat all OOD samples as a single class, despite real-world…
Li Liang, Shi-Ming Cai, Shi-Cai Gong, Alexandre G. Evsukoff + 1 more
Hypergraphs are powerful tools for modeling complex systems because they naturally encode higher-order interactions. However, most existing hypergraph representation-learning methods still struggle to capture such high-order structures, particularly in heterogeneous hypergraphs, which results in suboptimal performance…
Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park
One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph datasets. A critical challenge…
Takuto Takahashi, Itsuki Nakayama, Takahiro Mitani, Ryosuke Kikuchi + 2 more
Node classification in graph neural networks (GNNs) has been widely applied in various fields of graph analysis. GNNs achieve high-accuracy node classification in homophilous graphs, where nodes with the same class label tend to be connected. However, their performance remains limited in heterophilous graphs, where…
Sethupathy Parameswaran, Suresh Sundaram, Yuan Fang
Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) presents a significant…
Bo Xiao, Wei Yin, Stanisław Drożdż
Bitcoin transaction anomaly detection is essential for maintaining financial market stability. A significant challenge is capturing the dynamically evolving transaction patterns within transaction networks. Dynamic graph models are effective for characterizing the temporal evolution of transaction systems. However…
Maddalena M Bolognesi, Lorenzo Dall’Olio, Giulio Eugenio Mandelli, Luisa Lorenzi + 7 more
Lymph nodes (LN) are key secondary lymphoid organs (SLO) for a coordinated immune response. They have been extensively characterized by numerous investigative techniques chiefly as single cell suspensions because they are composed of vagile yet crowded hematolymphoid elements, unfriendly to spatial tissue…
Jiangnan Zhou, Sheng Zhang, Bing Wu, Qiuming Wang + 5 more
Existing methods for hypergraph node classification usually rely on local message passing and use a unified strategy for topological modeling across hyperedges of different sizes. However, they have two limitations in semi-supervised settings. First, representation learning mainly depends on local neighborhoods, making…
Nan Chen, Zemin Liu, Bryan Hooi, Bingsheng He + 2 more
In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional GNNs often struggle in such scenarios, as they tend to overfit to majority classes while underrepresenting minority…
Arooj Nissar, A. H. Mir
Background Computed tomography imaging, a non-invasive tool, is used around the globe by medical professionals to identify and diagnose lung cancer; a lethal disease with high rates of occurrence and mortality globally. Radiomics extracted from medical images, including computed tomography, in tandem with machine…
Kini Chen, Mohammad Torabi, Jie Jian, Archer Y. Yang + 1 more
Dynamic functional connectivity (dFC) studies the time-varying coordination between brain regions measured with fMRI and is a potential biomarker for understanding cognitive dynamics and tracking the development of neurological disorders. However, a critical methodological challenge lies in the variability of dFC…
Amin Khodaei, Zahra Pourabbas, Fatemeh Hashem-zadehdizajyekan, Erfan Esmaeili
Title: Highlights 1. • Modeling the structure of various viruses in the form of directed weighted graphs. 2. • Presenting a feature extraction algorithm based on complex networks metrics. 3. • The impact of the eigen-vector, input centrality and output centrality measures of specific nucleotide triplets within genes…
Diya Ramani
Rare diseases collectively affect over 300 million individuals worldwide, yet the vast majority lack approved pharmacological treatments, leaving patients with few therapeutic options and researchers with limited computational tools for systematic candidate identification. This study presents a network-based…
Muhammed Ali Pala, Muhammet Burhan Navdar, Jae-Ho Han
Background/Objectives: Traditional medical image analysis methods often suffer from locality bias, limiting their ability to model long-range contextual relationships between spatially distributed anatomical structures. To overcome this challenge, this study proposes SPX-GNN (Superpixel Explainable Graph Neural…
Miguel D. Fernández-de-Bobadilla, Val F. Lanza
Bacterial strain typing is key to surveillance, outbreak investigation and microbial ecology, yet current systems remain species-specific, reference-dependent and lack a universal, interpretable metric of genomic relatedness. Here, we introduce BacTaxID, a fully configurable, whole-genome k-mer-based framework that…
Abdullah Shaik, Anwar Said
We propose NetinfoGC, a framework for graph classification that extends the Network Usable Information (NUI) paradigm to graph-level learning. Unlike conventional graph neural network approaches that rely on end-to-end training of black-box embeddings, NetinfoGC constructs a family of permutation-invariant graph…
Authors not listed
Recent advances in generative artificial intelligence have enabled in silico molecular design to become a powerful approach for exploring chemical space toward specific design goals across various domains. However, in actual design workflows, determining the appropriate generation conditions, including generative…
Authors not listed
Graph Neural Networks (GNNs) are powerful tools for molecular property prediction, but they are not magic. When applied to molecules unlike their training data, they produce unreliable predictions that are difficult to detect. The Applicability Domain (AD) concept addresses this by defining regions of chemical space…
Caroline L. Alves, Simone Hufgard, Margot Mayer, Helena Dasch + 4 more
To address the limitations of calcium imaging data, we propose a segmentation-agnostic deep learning framework that integrates Quantile-Based Time-Series Network (QTN) representations with convolutional neural networks to classify neuronal dynamics across multiple spatial resolutions and acquisition frequencies. By…
Authors not listed
We present a new method for fingerprint- ing atomic configurations relevant to ML-IAM training and application, utilizing the ChIMES descriptor. These fingerprints enable rigor- ous analysis of statistical distinguishability be- tween configurations. Sample applications in- clude assessing diversity within ML-IAP…