graph neural networks

Edge weight concentration overcomes node degree blindness in graph based network intrusion detection

Graph-based network intrusion detection almost universally represents attacker behavior through node-centric structural features – degree, centrality, embeddings from graph neural networks – which implicitly assume that an attacker’s identity is visible as a distinct node in the host-communication graph. We show that t...

Title: Dynamical Topology Optimization for Complexity

Dynamical Topology Optimization (DTO) provides a framework for optimizing complex network topologies by iteratively refining connections based on emergent properties. This paper introduces a novel algorithm, termed 'Adaptive Topology Evolution', which integrates reinforcement learning and graph theory to achieve automa...

Fast Tri-Hybrid Beamforming via Deep Unfolding

Tri-hybrid multiple-input multiple-output architectures have recently emerged as a promising enabler for next-generation wireless systems, as they potentially provide enhanced design flexibility without a proportional increase in hardware cost or power consumption. However, the resulting triple-domain coupling renders...

Numerical simulation of D-Wave's quantum advantage experiment with time-dependent variational Monte Carlo

Programmable quantum annealers can realize real-time dynamics of frustrated transverse-field Ising models on large, nontrivial graphs. Recent work by King et al. argued that the classical simulation of such experiments would require exponential computational resources for classical methods such as tensor networks and n...

Closing the Semantic-Edge Gap: Tiny Language Models for 6G Wireless Intelligence

A two-axis taxonomy connecting six compression families to five semantic communication architectures is synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier, synthesized with a quantitative meta-analysis of the model-size-versus-semantic-fidelity Pareto frontier.

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.