← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 13 papers for 2026-03-30

Incorporating contextual information into KGWAS for interpretable GWAS discovery
Knowledge Graph

This paper extends KGWAS by incorporating contextual information into the knowledge graph workflow to improve GWAS interpretability and discovery power. By conditioning on context-specific biology rather than a single large general KG, it aims to yield more mechanistic, testable variant–gene–interaction findings.

Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?
GNN Graph Learning LLM × Graph

We propose a framework to assess the robustness of LLM-enhanced GNNs under poisoning attacks that manipulate both graph topology and textual features. The framework enables systematic evaluation and reveals how semantic features from LLMs affect vulnerability, guiding more robust designs.

DPD-Cancer: Explainable Graph-based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
GNN Graph Learning

DPD-Cancer is a graph-based deep learning pipeline for predicting small-molecule anti-cancer activity across cancer cell lines, with explanation capabilities. It integrates chemical structure and cellular context to capture non-linear relationships and heterogeneity, delivering interpretable predictions.

PEANUT: Perturbations by Eigenvalue Alignment for Attacking GNNs Under Topology-Driven Message Passing
GNN

PEANUT introduces a gradient-free, restricted black-box attack that perturbs GNNs by aligning eigenvalues and injecting virtual nodes to exploit topology-driven message passing. The method highlights a simple yet effective vulnerability of adjacency/Laplacian-based GNNs under topology perturbations.

On the Complexity of Optimal Graph Rewiring for Oversmoothing and Oversquashing in Graph Neural Networks
GNN Graph Theory Graph Learning

This work analyzes the computational complexity of optimally rewiring graph topology to mitigate oversmoothing and oversquashing in deep GNNs. It provides hardness results and theoretical limits, informing how feasible topology optimization is at scale.

Geometric Evolution Graph Convolutional Networks: Enhancing Graph Representation Learning via Ricci Flow
GNN Graph Theory Graph Learning

Geometric Evolution Graph Convolutional Networks (GEGCN) model geometric evolution on graphs using discrete Ricci flow, with an LSTM capturing the evolution and feeding dynamic representations into a GCN. Experiments show state-of-the-art performance on multiple classification benchmarks.

Topology-Aware Graph Reinforcement Learning for Energy Storage Systems Optimal Dispatch in Distribution Networks
Graph Learning

We propose a topology-aware RL framework for optimal dispatch of energy storage systems in distribution networks, using TD3 and GNN-based graph feature encoders to adapt to topology changes. The study systematically compares three GNN variants and demonstrates improvements in economic performance and voltage security.

D-GATNet: Interpretable Temporal Graph Attention Learning for ADHD Identification Using Dynamic Functional Connectivity
GNN Graph Learning

D-GATNet is an interpretable temporal graph attention network for ADHD identification from dynamic functional connectivity derived from fMRI. It models time-varying brain networks with attention mechanisms to improve classification and provide interpretable insights.

Vision Transformers and Graph Neural Networks for Charged Particle Tracking in the ATLAS Muon Spectrometer
GNN Graph Learning

This work combines Vision Transformers and Graph Neural Networks to improve charged particle tracking in the ATLAS Muon Spectrometer under high-luminosity conditions. The approach aims to robustly identify and reconstruct muons with higher efficiency in crowded environments.

Causal Graph Neural Networks for Healthcare
GNN Graph Learning

Causal Graph Neural Networks for Healthcare discusses combining graph-based representations with causal inference to learn invariant, cross-institutional mechanisms, addressing brittleness and biases in real-world deployments.

Reproducibility and Artifact Consistency of the SIGIR 2022 Recommender Systems Papers Based on Message Passing
GNN Graph Learning

The paper assesses reproducibility and artifact consistency of SIGIR 2022 graph-based recommender system papers, identifying gaps in data, code, evaluation, and reporting. It offers recommendations to improve methodological rigor and replicability.

ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation
Knowledge Graph Graph Learning

ReCUBE introduces a benchmark to measure how effectively LLMs leverage repository-level context for code generation, by tasking them to reconstruct a masked file using remaining code and project context. It reveals variability in contextual utilization across models.

To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Knowledge Graph LLM × Graph

The study argues that simply exposing private-library API docs is insufficient for accurate private-library code generation. It explores methods to teach LLMs to effectively use private libraries for code generation, focusing on instruction and training strategies that enhance API invocation.