← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph
Conferences
Archives
2026-08-11 2026-08-10 2026-08-09 2026-08-08 2026-08-07 2026-08-06 2026-08-05 2026-08-04 2026-08-03 2026-08-02 2026-08-01 2026-07-31 2026-07-30 2026-07-29 2026-07-28 2026-07-27 2026-07-26 2026-07-25 2026-07-24 2026-07-23 2026-07-22 2026-07-21 2026-07-20 2026-07-19 2026-07-18 2026-07-17 2026-07-16 2026-07-15 2026-07-14 2026-07-13 2026-07-12 2026-07-11 2026-07-10 2026-07-09 2026-07-08 2026-07-07 2026-07-06 2026-07-05 2026-07-04 2026-07-03 2026-07-02 2026-07-01 2026-06-30 2026-06-29 2026-06-28 2026-06-27 2026-06-26 2026-06-25 2026-06-24 2026-06-23 2026-06-22 2026-06-21 2026-06-20 2026-06-19 2026-06-18 2026-06-17 2026-06-16 2026-06-15 2026-06-14 2026-06-13 2026-06-12 2026-06-11 2026-06-10 2026-06-09 2026-06-08 2026-06-07 2026-06-06 2026-06-05 2026-06-04 2026-06-03 2026-06-02 2026-06-01 2026-05-31 2026-05-30 2026-05-29 2026-05-28 2026-05-27 2026-05-26 2026-05-25 2026-05-24 2026-05-23 2026-05-22 2026-05-21 2026-05-20 2026-05-19 2026-05-18 2026-05-17 2026-05-16 2026-05-15 2026-05-14 2026-05-13 2026-05-12 2026-05-11 2026-05-10 2026-05-09 2026-05-08 2026-05-07 2026-05-06 2026-05-05 2026-05-04 2026-05-03 2026-05-02 2026-05-01 2026-04-30 2026-04-29 2026-04-28 2026-04-27 2026-04-26 2026-04-25 2026-04-24 2026-04-23 2026-04-22 2026-04-21 2026-04-20 2026-04-19 2026-04-18 2026-04-17 2026-04-16 2026-04-15 2026-04-14 2026-04-13 2026-04-12 2026-04-11 2026-04-10 2026-04-09 2026-04-08 2026-04-07 2026-04-06 2026-04-05 2026-04-04 2026-04-03 2026-04-02 2026-04-01 2026-03-31 2026-03-30 2026-03-29 2026-03-28 2026-03-27 2026-03-26 2026-03-25 2026-03-24 2026-03-23 2026-03-22 2026-03-21 2026-03-20 2026-03-19 2026-03-18 2026-03-17 2026-03-16 2026-03-15 2026-03-14 2026-03-13 2026-03-12 2026-03-11 2026-03-10 2026-03-09 2026-03-07 2026-03-06 2026-03-05 2026-03-04 2026-03-03 2026-03-02 2026-03-01 2026-02-28 2026-02-27 2026-02-26 2026-02-25 2026-02-24 2026-02-23 2026-02-22 2026-02-21 2026-02-20 2026-02-19 2026-02-18 2026-02-17 2026-02-16 2026-02-15 2026-02-14 2026-02-13 2026-02-12

Showing 18 papers for 2026-06-15

SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting
Graph Learning

We propose SpikF-GO, a spiking Fourier graph operator for multivariate time series forecasting. The method uses spiking neural networks to model inter-variable dependencies and processes data in the Fourier domain to capture temporal patterns while maintaining energy efficiency.

PostDeg: Placement Beats Parameterization in LayerNorm GNNs
GNN

PostDeg identifies the best placement of a per-node scalar in LayerNorm GNNs. A positive scalar inserted before LayerNorm is canceled by normalization, while a scalar inserted after LayerNorm affects the representation magnitude at the score head. The surviving slot is the post-LayerNorm position, implemented as a parameter-free PostDeg that improves stability and performance.

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems
Graph Learning

Graph-based Target Back-Propagation GTBP offers a context adaptation framework for multi-LLM agentic systems. The framework models agentic workflows as directed acyclic graphs and propagates local target outputs backward to revise prompts, addressing credit assignment and convergence guarantees.

Curvature-Informed Potential Energy Surface for Protein-Ligand Binding Affinity Prediction
Graph Learning

We propose Curvature-Informed Potential Energy Surface CPES graph neural net for protein ligand binding affinity prediction. By incorporating curvature information from the molecular energy landscape and by accounting for binding induced conformational changes, CPES improves predictions beyond static conformations.

Graph Structured Combinatorial Semi-Bandit with Nonlinear Reward Associations through Separable Signals
Graph Learning

We develop a graph structured combinatorial semi-bandit framework with nonlinear reward associations through separable signals. The approach combines graph based causal reward modeling, analytic reproducing kernel methods, and Taylor approximations to capture nonlinear reward dependencies and improve learning efficiency.

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response
Graph Learning

We present a safety contract graph MARL framework for autonomous network security response. The architecture named ACD3-GAT separates simulator observations from reusable operational budgets and uses constrained optimization with graph state encoding to enable deployable policies.

Temporally Consistent Graph Q-Networks for Intelligent Network Control
GNN Graph Learning

We propose Temporally Consistent Graph Q-Networks for intelligent network control. The method learns a self predicting representation of the whole network to achieve temporal consistency in high level control tasks.

Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling
Knowledge Graph Graph Learning

We introduce Knowledge Graph Enhanced Memory Augmented Retrieval for long context modeling. The system builds dynamic knowledge graphs from input during inference to support memory augmented retrieval, combining semantic similarity with explicit entity relations for domain adaptive retrieval.

When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More
GNN Graph Learning

We study how LLM agents use GNN tools. Using a frozen GNN as a tool, we find that agents tend to defer to the GNN rather than exercising judgment, and their predictions align with the raw GNN in the vast majority of cases.

From Small to Large: A Graph Convolutional Network Approach for Solving Assortment Optimization Problems
GNN Graph Learning

From Small to Large proposes a Graph Convolutional Network approach for constrained assortment optimization. The method builds a graph representation of the problem and trains a GCN to map problem instances to high performing assortments under constraints.

Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
GNN Graph Learning

Tackling GNARLy Problems reframes neural algorithmic reasoning as a reinforcement learning task. By modeling algorithm trajectories as a Markov decision process, the approach addresses post processing validity, multiple correct solutions, and scalability to NP-hard problems.

Generalizing GNNs with Tokenized Mixture of Experts
GNN Graph Learning

Generalizing GNNs with Tokenized Mixture of Experts introduces instance conditional routing to select among experts for GNN inference. This helps stabilize learning and improves generalization under distribution shifts while maintaining computational efficiency.

Quantile-Free Uncertainty Quantification in Graph Neural Networks
GNN Graph Learning

Quantile-Free Uncertainty Quantification in Graph Neural Networks introduces QpiGNN, a framework that builds prediction intervals without quantile estimation by directly optimizing a quantile regression inspired objective. It enables UQ in GNNs with reduced computational cost.

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters
Knowledge Graph Graph Learning

CuMA aligns LLMs with sparse cultural values using a demographic aware mixture of adapters. Dense models exhibit mean collapse under conflicting value distributions, and CuMA uses culture conditioned adapters to capture diverse cultural modes.

AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
GNN Graph Learning

AdaTKG proposes adaptive memory for temporal knowledge graph reasoning. Entities are modeled as adaptive processes whose representations are refined at each interaction, enabling dynamic reasoning over evolving events.

Hyperdimensional computing for structured querying on tabular data embeddings
Knowledge Graph Graph Learning

Hyperdimensional computing for structured querying on tabular data embeddings proposes using hyperdimensional representations to enable interpretable similarity scores for tabular embeddings. This approach provides more transparent similarity measures than traditional nearest neighbor or black box distances.

GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
GNN Graph Learning

GMN4AD presents a graph matching network for Alzheimer's disease diagnosis with test-time domain adaptation across multi-centered MRI data. The method aligns data distributions at test time to improve cross-site diagnostic performance.

ChronoID: Infusing Explicit Temporal Signals into Semantic IDs for Generative Recommendation
Knowledge Graph

ChronoID infuses explicit temporal signals into semantic IDs for generative recommendation. By differentiating semantic IDs across temporal contexts, ChronoID improves recommendation quality in time dependent settings.