Tag
GAE introduces a framework combining graph neural networks, reinforcement learning, and LLM fine-tuning to overcome bottlenecks in evolutionary program search, achieving state-of-the-art performance on symbolic regression for complex nonlinear oscillator systems.
Presents a Variational Graph Autoencoder (VGAE) for detecting power flow solution feasibility in electric power networks, using the IEEE 118-bus case. The method distinguishes between problem infeasibility and algorithm non-convergence.
This paper introduces a graph neural network model for real-time hand gesture recognition using surface electromyography (sEMG) signals from the forearm. The method achieves 99% classification accuracy with an average processing time of 48ms on an M1 Pro CPU, outperforming existing state-of-the-art techniques.
STAGformer introduces a spatio-temporal agent graph transformer with linear complexity for bike-sharing demand forecasting, outperforming baselines on NYC and Chicago datasets.
SafeImpute proposes a reliable imputation framework for irregular clinical data using graph neural networks and conformal selection to control the false discovery rate of clinically unacceptable errors.
This paper proposes a geometry-aware multi-support heterogeneous graph neural network for fine-scale rainfall field reconstruction, which fuses observations from point gauges, path-integrated microwave links, and gridded radar/satellite data. The method reduces RMSE by 23.2% over classical interpolation on Singapore data and shows greatest gains when the field is undersampled relative to its spatial correlation length.
EO-Agents presents a three-agent LLM pipeline for generating Earth observation hypotheses, leveraging a NASA knowledge graph and graph neural network to rank candidate dataset pairings, with LLM agents filtering, generating, and evaluating structured research hypotheses.
MKGR is a multimodal framework that combines protein sequence encoding with four biomedical knowledge graphs to improve cold-start protein-protein interaction prediction, outperforming baselines on benchmark datasets.
X-LogSMask introduces a logarithmic structural mask for graph transformers, injecting graph topology directly into attention logits to achieve state-of-the-art performance on 13 out of 20 benchmarks while preserving interpretability and multi-hop information propagation.
GRAB uses a GNN encoder to convert relational tables into latent tokens for frozen LLMs, achieving significant performance gains in multi-table question answering.
This paper presents a latent dynamical model using a heart-rate-aware neural ODE and graph-based mesh autoencoder to model full-cycle ventricular motion from cine cardiac MRI. Applied to 72,386 UK Biobank participants, the model improves heart failure risk prediction over conventional cardiac markers.
Proposes G-SPIN, a lightweight framework that combines phonetic graph modeling with contextual language understanding for correcting ASR errors, using a GNN to generate phonetically plausible candidate tokens, an MLM for local scoring, and an LLM for final re-ranking, all operating at inference time.
This paper proposes MVG-KAN, a multi-view model integrating periodic-residual decomposition, a Geo-Wind Graph for wind-aware spatial dependencies, and a temporal KAN head for PM2.5 forecasting, achieving MAE 14.09 on Beijing data.
This paper proposes SenFlow, a method for sentence-level AI-generated text detection in hybrid documents by modeling inter-sentence dependencies using graph propagation and linear-chain CRF decoding. It also introduces the MOSAIC benchmark with 16,000 documents generated by DeepSeek-V3.2 and Kimi K2, achieving state-of-the-art performance.
Proposes TMR-GGNN, a time-aware multi-relational graph neural network for credit card fraud detection that handles imbalanced data and evolving fraud patterns via contrastive learning and focal loss.
This paper presents an advanced GNN surrogate for forecasting CO2 plume migration in complex geological formations, introducing an anisotropic message-passing mechanism to handle directional transport, aiming to accelerate carbon capture and storage simulations.
This paper proposes CPES, a curvature-informed potential energy surface graph neural network for protein-ligand binding affinity prediction. It integrates physics-informed curvature representations to model conformational flexibility and achieves improved predictive performance on benchmark datasets.
TAROT proposes a GNN-based framework that leverages LLMs to construct and refine task-adaptive semantic graphs for few-shot tabular learning, achieving state-of-the-art performance.
This paper introduces GLACIER, a multimodal student-teacher foundation model that integrates molecular graphs, SMILES strings, and physicochemical descriptors to predict molecular properties efficiently. It leverages Finsler geometry-aware fusion and knowledge distillation from larger teacher models (MiniMol, MolFormer) to achieve high performance with a lightweight architecture.
OSMGraphCLIP is a model that learns global location embeddings from OpenStreetMap data using a graph-based encoder and contrastive alignment with a spherical-harmonics location encoder. It achieves strong performance across diverse geospatial tasks, often matching or exceeding satellite-based methods.