Latest posts tagged with #GraphNeuralNetworks on Bluesky
EGATE-NNVQE combines a graph autoencoder with a neural network to generate VQE parameters that generalize across unseen Hamiltonians without retraining, achieving up to 69% error reduction and significantly milder barren plateau decay vs. standard VQE.
#QuantumComputing #VQE #GraphNeuralNetworks
Vector database that actually learns from your queries - stores embeddings, queries with Cypher like Neo4j, scales with Raft consensus, and improves search results using Graph Neural Networks
https://github.com/ruvnet/ruvector
#VectorDatabase #GraphNeuralNetworks #Rust
2026 is the year GNN‑LLM hybrids leave the lab and power real‑world AI. Adaptive, context‑aware models are finally scaling for enterprise workloads. Dive into how graph‑neural nets and LLMs are teaming up! #GraphNeuralNetworks #GNNLLM #EnterpriseAI
🔗 aidailypost.com/news/2026-ma...
Layer-to-Layer Knowledge Mixing in Graph Neural Network for Chemical
Property Prediction
Daokun Zhang, David K. Chalmers et al.
Paper
Details
#GraphNeuralNetworks #ChemicalPropertyPrediction #LayerWiseKnowledgeMixing
New Taxonomy Clarifies Higher-Order Graph Neural Networks
A new taxonomy for higher-order graph neural networks has been released, clarifying their classification. Read more: getnews.me/new-taxonomy-clarifies-h... #graphneuralnetworks #taxonomy #machinelearning
NatGVD: Natural Adversarial Attack on Graph‑Based Vulnerability Detection
NatGVD achieves up to 53.04% natural adversarial evasion against GNN‑based and transformer vulnerability detectors, per a study submitted on 6 Oct 2025. getnews.me/natgvd-natural-adversari... #graphneuralnetworks #adversarialattack
Graph-Based Tabular Deep Learning Needs to Model Feature Interactions
Position paper (6 Oct 2025) shows graph‑based tabular deep learning often misses true feature‑interaction graphs; enforcing the correct graph boosts performance. Read more: getnews.me/graph-based-tabular-deep... #graphneuralnetworks #neurips
Disentangled Multiplex Graph Paper for POI Recommendation Withdrawn
The authors have formally withdrawn their study on the DiMuST model for point‑of‑interest recommendation, citing a need for major manuscript restructuring. Read more: getnews.me/disentangled-multiplex-g... #pointofinterest #graphneuralnetworks
Graph Neural Networks Enhance Power Grid Topology Control
A study finds that a heterogeneous graph neural network outperforms homogeneous GNNs and a fully‑connected NN in predicting optimal topology‑control actions on unseen grid configurations. getnews.me/graph-neural-networks-en... #graphneuralnetworks #powergrid
Sequential Graph Neural Networks Boost Combinatorial Graph Alignment
Bootstrapped graph neural networks refine node‑pair similarity, achieving three times higher alignment accuracy and solving cases where prior methods failed. Read more: getnews.me/sequential-graph-neural-... #graphneuralnetworks #graphalignment
VisitHGNN Graph Neural Network Predicts Urban POI Visit Patterns
VisitHGNN, a heterogeneous graph neural network, predicts POI visit probabilities with a Top‑1 accuracy of 0.853 and R‑square of 0.892 in Fulton County, GA. Read more: getnews.me/visithgnn-graph-neural-n... #visithgnn #graphneuralnetworks #urbanmobility
Graph Neural Networks Identify Asymptomatic Spreaders in Epidemics
A graph neural network detects asymptomatic carriers in epidemic models, achieving precision and recall. Tested on Erdős‑Rényi, scale‑free and small‑world networks. Read more: getnews.me/graph-neural-networks-id... #graphneuralnetworks #epidemics
Hierarchy-Aware Neural Subgraph Matching Boosts Accuracy and Speed
NC‑Iso improves subgraph matching accuracy while keeping fast inference, outperforming prior GNN models on nine benchmark datasets. Code released on GitHub. Read more: getnews.me/hierarchy-aware-neural-s... #nciso #graphneuralnetworks
Graph Neural Networks Enable Proactive Mobility Management in O‑RAN
Researchers propose a proactive O‑RAN handover framework using graph neural network link prediction, outperforming statistical methods. The GNNs were tested on data. getnews.me/graph-neural-networks-en... #orannetwork #graphneuralnetworks
Differential Encoding Boosts Graph Neural Network Representations
A differential encoding improves GNN embeddings by contrasting node and neighbor features, boosting performance on 7 datasets. In IEEE Transactions on Big Data (Sept 2025). Read more: getnews.me/differential-encoding-bo... #graphneuralnetworks #bigdata
Interpretable Jet Physics with IRC‑Safe Equivariant Neural Networks
Researchers unveiled graph networks that enforce IRC safety and E(2)/O(2) equivariance, matching quark‑gluon classification accuracy; the study was submitted on 26 September 2025. getnews.me/interpretable-jet-physic... #ircsafety #graphneuralnetworks
New Graph Neural Network Boosts EEG-Based Depression Diagnosis
New AI model ELPG‑DTFS reaches 97.63% accuracy and 97.33% F1 on a 53‑person, 128‑channel EEG MODMA dataset, improving depression screening with adaptive graph learning. Read more: getnews.me/new-graph-neural-network... #depression #eeg #graphneuralnetworks
New Graph Neural Network Improves Multivariate Time Series Forecasting
DIMIGNN, a new graph neural network, picks diverse neighbors and fuses multiple temporal scales, delivering lower forecast errors on electricity demand and traffic flow data. getnews.me/new-graph-neural-network... #graphneuralnetworks #forecasting
Pure Node Sampling Tackles Class Imbalance in Graph Neural Networks
Pure Node Sampling (PNS) module balances class ratios and topology in GNNs, significantly reducing variance. The arXiv preprint was posted on 28 September 2025. Read more: getnews.me/pure-node-sampling-tackl... #graphneuralnetworks #classimbalance
Caterpillar GNN Offers Efficient Walk-Based Aggregation
Caterpillar GNN replaces message‑passing with walk‑based aggregation, using far fewer hidden nodes while matching the predictive accuracy of leading MPGNNs on real‑world data. getnews.me/caterpillar-gnn-offers-e... #caterpillargnn #graphneuralnetworks
RsGCN Improves Generalization of GCN Solvers for TSP
RsGCN, a graph convolutional network, was trained on TSP instances of up to 100 nodes and, after just three epochs, can generalize to 10 000‑node problems without fine‑tuning. Read more: getnews.me/rsgcn-improves-generaliz... #rsgcn #tsp #graphneuralnetworks
Learnable Kernel Density Estimation Advances Graph Neural Networks
LGKDE merges graph neural networks with learnable kernel density estimation, beating state‑of‑the‑art baselines on several graph anomaly‑detection benchmarks. getnews.me/learnable-kernel-density... #graphneuralnetworks #densityestimation
Graph-Based Model Boosts Account Takeover Detection by 6%
ATLAS, a spatio‑temporal graph framework for account takeover detection, raised AUC by 6.38% over XGBoost and cut user friction by over 50% in Capital One’s live testing. Read more: getnews.me/graph-based-model-boosts... #graphneuralnetworks #frauddetection
Graph Neural Network Entropy Model Enhances Vital Node Detection
GNNE merges GCN and GAT with entropy to spot vital nodes, outperforming eight topology‑based and four graph‑ML methods on a synthetic Barabási–Albert network and six real‑world datasets. getnews.me/graph-neural-network-ent... #gnne #graphneuralnetworks
FedIA Enhances Federated Graph Learning with Gradient Pruning
FedIA keeps only the top 5 % of gradient coordinates, raising accuracy. Tested on Twitch gamers and multilingual Wikipedia graphs, it outperformed baselines. Read more: getnews.me/fedia-enhances-federated... #federatedlearning #graphneuralnetworks
Graph Neural Networks Power Self‑Supervised Neural Circuit Discovery
Self‑supervised graph‑neural model infers synaptic connections, validated on synthetic ring attractors and mouse head‑direction data. Submitted 21 Sep 2025, NeurIPS 2025. getnews.me/graph-neural-networks-po... #graphneuralnetworks #neurips
TF-DWGNet: Directed Weighted Graph AI Boosts Cancer Subtype Classification
TF-DWGNet builds directed weighted graphs per omics layer and merges them via low‑rank tensor fusion, achieving high accuracy on cancer subtype datasets. Read more: getnews.me/tf-dwgnet-directed-weigh... #cancersubtype #graphneuralnetworks
Unrolled Graph Neural Networks for Constrained Optimization
A new method unrolls the dual ascent algorithm into paired graph neural networks, delivering near‑optimal and near‑feasible results; the paper was posted on 21 September 2025. Read more: getnews.me/unrolled-graph-neural-ne... #graphneuralnetworks #dualascent
Graph-Based Point Cloud Surface Reconstruction Using B‑Spline AI
A paper released on 19 Sep 2025 proposes a network that predicts placement of B‑spline control points, enabling smooth reconstruction of noisy point clouds without normals. getnews.me/graph-based-point-cloud-... #graphneuralnetworks #bspline
Guiding Graph Neural Networks Toward Fairness with New Links
FairGuide adds new edges to graphs, using meta‑gradients to boost fairness, and experiments on benchmark datasets show consistent fairness gains while preserving performance. Read more: getnews.me/guiding-graph-neural-net... #graphneuralnetworks #fairness
