graph neural networks

Cryptic Binding Site Prediction Using Equivariant Graph Neural Networks with Kolmogorov-Arnold Networks.

CrypKANet is an innovative multimodal predictive framework for cryptic binding site identification that integrates EGNN, gated attention mechanisms, and Kolmogorov-Arnold Network (KAN) and exhibits excellent generalization performance on protein-protein interaction sites and ligand binding site tasks.

Dual Graph Network Hashing for Cross-Modal Retrieval

Hashing algorithms represent data by generating compact binary hash codes, enabling efficient cross-modal similarity search and significantly improving the storage efficiency and retrieval performance of image-text data. However, because traditional hashing methods typically separate image-text feature extraction from...

Design a Gaussian mixture-based clustering model for enhancing accuracy and robustness in smart homes

GMM equal is the most balanced topology, with the best balance between reliability, efficient communication, and scalability when applied to the internet of things and smart homes.

Modeling link recommendations as a network growth mechanism and their impact on social contagion

It is shown that while simple contagions exhibit relatively modest shifts under most recommenders, complex contagions are highly sensitive to clustering-and homophily-based recommendations, thriving at moderate recommendation strengths but sharply diminishing under excessive recommendation strength.

Element priors and target support shape chemical transfer in materials graph networks

Target support shifts chemical transfer from reliance on static element relations toward learning from target-containing environments, and freezing the initial element projection preserves most gains in five of six ALIGNN splits.

SafePowerGraph: A safety-aware benchmarking framework for scalable graph neural networks in power flow and optimal power flow

Topology-aware GNNs under structural perturbations: Empirical robustness across domains

Results support a conditional empirical conclusion: combining structure, topology, and stability-oriented training can improve robustness under specified structural perturbations, with dataset-dependent accuracy–stability trade-offs rather than universal guarantees.

Insider Threat Prediction Using Graph Analysis

The findings demonstrate the effectiveness of the graph-based methods in providing high-quality behavioral dependencies, with better accuracy and fewer false alarms and greater explainability in real-life insider risk monitoring.

Contextualized Semantic Graph Neural Networks

This paper introduces Contextualized Semantic Graph Neural Networks (CSGNNs), a novel approach to graph representation learning that addresses the inherent limitations of static graph embeddings. Existing graph neural networks often struggle to adapt to evolving semantic relationships within graphs, primarily due to th...

基于自适应神经网络的图论推理

This paper introduces a novel graph theory reasoning framework based on adaptive neural networks. Traditional graph theory reasoning methods often rely on fixed models, limiting their effectiveness in complex graph problems. Our proposed approach leverages adaptive neural networks to address these limitations, offering...

基于图神经网络的拓扑分析

This paper introduces a novel approach to topology analysis utilizing graph neural networks (GNNs). We propose a method for automatically constructing and analyzing complex topology graphs, with the capability to predict and optimize topological structures. Traditional approaches rely on manual graph construction, whic...

LibXSub: A Framework for Detecting Binary Third-Party Library Reuse Regions Based on Explanatory Subgraphs

Binary third-party library detection is a fundamental task in software composition analysis, vulnerability tracing, and software supply chain security. Existing approaches mainly rely on function-level matching or global similarity computation, while paying insufficient attention to region-level reuse structures formed...