← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 19 papers for 2026-05-23

Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
GNN Graph Learning Knowledge Graph LLM × Graph

Ex-GraphRAG replaces the GNN encoder with a Multivariate Graph Neural Additive Network (M-GNAN) to make evidence routing in Graph-Augmented LLMs interpretable. It addresses the inability to audit node contributions caused by iterative neighborhood aggregation and enables faithful auditing of which retrieved entities influenced the model output.

Efficient Higher-order Subgraph Attribution via Message Passing
GNN Graph Learning

We show that higher-order subgraph attribution via GNN-LRP can be computed efficiently with a new message-passing approach that avoids summing exponentially many walks. The method significantly reduces computational complexity, making practical, higher-order explanations feasible.

Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers
Graph Learning

We study three graph tokenizations for Transformers—spectral, random-walk, and adjacency—and show that tokenization fundamentally constrains transformer expressivity. Different tokenizations induce distinct depth regimes and performance trade-offs, underscoring the importance of tokenization design for graph-aware transformers.

Implicit Regularization of Mini-Batch Training in Graph Neural Networks
GNN Graph Learning

Mini-batch training of GNNs induces implicit regularization through subgraph sampling. The simplest scheme, Random Node Sampling (RNS) on the induced subgraph, matches or even beats full-graph training on most datasets while saving substantial training time.

Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
GNN Graph Learning

We evaluate deep ensembles for message-passing GNNs and find surprisingly limited gains in uncertainty quantification. Across seven datasets, ensembles provide little improvement over a strong single model, with any gains mainly arising from better single-model performance or calibration.

Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks
GNN Graph Learning

We systematically compare four explanation methods (SA, Integrated Gradients, GNNExplainer, and Layer-wise Relevance Propagation) for disease-relevant structure in a breast cancer RNA-seq projected PPI network. Using synthetic benchmarks with ground-truth, we show that explanations reveal a topological signature of disease-associated hubs, supporting biologically meaningful interpretability.

A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
GNN Graph Learning

A2QTGN is a hybrid quantum-classical framework that couples adaptive amplitude encoding with a Temporal Graph Network backbone for dynamic link prediction. By integrating quantum-inspired encoding with a scalable GNN, it aims to better capture concurrent and rapidly changing interactions in large dynamic graphs.

SPECTRA: Spectral Domain-Aware Graph Generation for Imbalanced Molecular Property Regression
Graph Learning

SPECTRA is a spectral-domain-aware graph generation method designed to improve regression for underrepresented molecular property values. It uses a rarity-aware budgeting scheme to focus generation where data is scarce, boosting predictive accuracy in highly relevant but under-sampled ranges.

Billion-Scale Graph Foundation Models
Graph Learning

Billion-Scale Graph Foundation Models (GraphBFF) present a practical recipe for building billion-parameter GFMs on large-scale heterogeneous graphs. The work outlines a GraphBFF Transformer and end-to-end pretraining and adaptation strategies to enable scalable, real-world graph foundation models.

Geometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs
GNN Graph Learning

Geometry-Induced Diffusion on Graphs introduces mu-ChebNet, a spectral GNN that learns a node-wise weight function mu before applying Chebyshev filters. The learned mu modifies the propagation geometry via a weighted Laplacian without changing the graph topology, improving long-range information diffusion.

MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?
Graph Learning LLM × Graph

MapTab is a multimodal benchmark to assess MLLMs on multi-criteria route planning in heterogeneous graphs. It requires models to ground map visuals and route attributes (e.g., time, cost) and perform holistic reasoning under multiple criteria.

Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models
Graph Learning LLM × Graph

Beyond One-Size-Fits-All proposes adaptive subgraph denoising for zero-shot graph learning with LLMs. By denoising subgraphs to improve cross-modal alignment between graphs and text, it enhances zero-shot predictive performance.

MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels
Graph Learning LLM × Graph

MemReward presents a graph-based experience memory for LLM reward prediction under limited labels. The memory stores past rollout experiences to help predict rewards when ground-truth labels are scarce, reducing annotation burden.

Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
GNN Graph Learning

Position argues that graph condensation should move beyond full-dataset training and model-dependent methods. The paper advocates resetting and developing model-agnostic condensation strategies to improve scalability and robustness for large graphs.

Format-Constraint Coupling in Knowledge Graph Construction from Statistical Tables
Knowledge Graph

Format-Constraint Coupling shows that on statistical tables, the interaction between serialization format and schema constraints can affect knowledge graph fidelity in a super-additive way. The results demonstrate that applying a schema to a mismatched format can trigger substantial degradation across datasets.

Knowledge Graph Re-engineering Along the Ontological Continuum (extended version)
Knowledge Graph

Knowledge Graph Re-engineering Along the Ontological Continuum advocates re-engineering KG representations along an ontological continuum to support neuro-symbolic AI. It discusses aligning vocabularies, axioms, and ontologies and leveraging GenAI automation to improve KG interoperability and reuse.

Dynamic Hypergraph Representation Learning for Multivariate Time Series without Prior Knowledge
GNN Graph Learning

Dynamic Hypergraph Representation Learning builds dynamic hypergraphs from multivariate time series without prior structure. The model learns hypergraph representations that capture higher-order relationships across variables as time evolves.

Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
Knowledge Graph Graph Learning

Case-Aware Medical Image Classification uses multimodal knowledge graphs and reliability-guided refinement to enable case-aware reasoning for explainable medical image diagnosis. Given an image, the method integrates historical similar cases and symptoms to support diagnosis with reliability-aware refinements.

CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials
LLM × Graph Graph Learning

CatalyticMLLM proposes a Graph-Text Multimodal LLM for catalytic materials, unifying graph-based representations with text modalities to address inconsistencies between generation and property-prediction spaces. This integration aims to improve property prediction and enable more effective generation-driven inverse design.