Tag
This paper proposes a confusion matrix-based graph construction method and a hybrid loss function for Graph Neural Networks to improve multi-site pollution prediction accuracy and interpretability, evaluated on real-world air pollution data.
Proposes DCQ-GNN, a spectral GNN that uses a compact bank of adaptive convex-concave quadratic filters to improve spectral selectivity without high-order polynomials, achieving competitive results on both homophilic and heterophilic graphs.
This paper presents a deep learning approach using a spatio-temporal graph neural network (MTGNN) to reconstruct GRACE terrestrial water storage anomalies back to 1940 for South America, achieving high accuracy and outperforming previous methods with fewer predictors.
This paper introduces FedEPD, a framework for federated graph learning under long-tailed data distributions. It uses an energy-guided dual decoupling approach to separate topological purification from semantic recalibration, achieving state-of-the-art performance on benchmarks with up to 4.97% accuracy improvement.
ModTGCN is a modularity-aware graph neural network that jointly optimizes cross-entropy and a modularity-based auxiliary objective to improve text classification by leveraging global community structure in document graphs, achieving consistent gains on five benchmarks.
MOLAR proposes a noise-aware framework for learning multimodal molecular representations from noisy labels by separating clean-property inference from observed label noise, outperforming baselines on molecular benchmarks.
This paper proposes a K-Hop Gaussian (KHG) diffusion kernel as a preprocessing module for graph neural networks, balancing local and global information propagation to mitigate over-smoothing and information bottlenecks. Experiments show significant improvements over traditional message-passing GNNs and existing diffusion kernels, especially on noisy or structurally complex graphs.
Artemis proposes a region-level causal framework that learns region-specific confounder representations to eliminate demographic confounders in multimodal neuroimaging, improving graph neural network performance on disease diagnosis and classification tasks.
This paper establishes a semantic framework linking graph neural network classifiers to fragments of graded modal logic, showing that preservation under structural properties like embeddings and homomorphisms corresponds to specific logical fragments. It provides characterizations independent of architectural choices and demonstrates that each class admits a GNN architecture of equivalent expressiveness.
This paper proposes a Finslerian graph neural network that estimates the Finsler Laplacian on point clouds, proving convergence and demonstrating its use in recovering Finsler metrics from heat diffusion.
This paper compares 19 graph neural network layer types for modelling interactions in driving trajectory prediction, finding ARMA, Chebyshev, and topology-aware layers most effective and offering design principles for better prediction models.
This paper empirically tests whether LLM agents with GNN tools exercise judgment or blindly obey the tool, finding that agents agree with the GNN 97.6–99.2% of the time and that stronger backbones defer even more. The cost of this deference does not shrink with capability, and selective invocation remains an open problem.
Proposes CoMAG, a unified backbone for multimodal attributed graphs that learns task-adaptive reliable contexts and performs modality-preserving alignment, achieving state-of-the-art results on graph-level prediction, modality matching, and graph-conditioned generation.
This paper proposes RicciBind, a geometric representation framework that integrates Ricci curvature and optimal transport for protein-ligand binding affinity prediction, demonstrating superior accuracy and interpretability across benchmarks.
This paper identifies that in LayerNorm-based GNNs, positive per-node scalars like node degree are erased when placed before LayerNorm but survive after LayerNorm. The authors propose PostDeg, a parameter-free post-LayerNorm inverse-degree scale, achieving significant gains on influence maximization, network dismantling, and maximum independent set tasks.
Introduces SpikF-GO, a spiking neural network model for multivariate time series forecasting that combines graph-based inter-variable dependency modeling with spike-driven spectral processing, achieving state-of-the-art results among SNN methods with reduced energy consumption.
TacticAI uses graph neural networks to represent players as nodes and their interactions as connections, allowing data scientists to test defensive setups by dragging and dropping players in real time.
Introduces GraphInfer-Bench, a benchmark to evaluate whether LLMs can perform graph inference—producing open-ended answers about a node and its neighborhood that cannot be retrieved from a single node or path. Experiments show that even frontier LLMs lag behind plain GNNs on these tasks, revealing a capability gap.
This paper applies graph neural networks to predict the solvability of finite groups, demonstrating an AI-driven approach to a classic problem in group theory.
Proposes a topological framework for comparing trained Graph Neural Networks by mapping Stochastic Block Model embeddings onto the n-sphere, enabling visual inspection and transfer-learning candidate retrieval without retraining.