← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 15 papers for 2026-03-06

An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs
GNN Graph Learning Knowledge Graph

This paper proposes an LLM-guided query-aware inference system to accelerate GNN inference on large knowledge graphs by tailoring computations to each query's structure and semantics. It argues that existing acceleration methods like pruning, quantization, and distillation treat models monolithically and miss query-specific adaptation. The system aims to improve efficiency without sacrificing accuracy.

Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
GNN Graph Learning

This work studies clean-label backdoor attacks on Graph Neural Networks, showing that triggers can be injected without relabeling training nodes, making stealthy poisoning feasible in realistic settings. It analyzes the limitations of conventional backdoor strategies and proposes mechanisms for such clean-label attacks. The results demonstrate practical viability and raise security concerns for GNN deployments.

Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs
GNN Graph Learning

We introduce Geometric-Aware Quantization (GAQ) for SO(3)-equivariant GNNs to compress and accelerate models without destroying rotational symmetry. Naive quantization breaks the equivariance and harms conservation laws, so GAQ preserves geometric structure while improving efficiency. The framework enables faithful physics-consistent simulations at lower cost.

Robust Node Affinities via Jaccard-Biased Random Walks and Rank Aggregation
Graph Learning Graph Theory

We propose TopKGraphs, a node-affinity method based on start-node biased random walks that emphasize transitions to structurally similar neighborhoods measured by Jaccard similarity. Instead of computing full stationary distributions, the walks act as stochastic neighborhood samplers, producing partial rankings that are robustly aggregated.

On the Necessity of Learnable Sheaf Laplacians
GNN Graph Learning

This paper questions whether learnable restriction maps in sheaf Laplacians are necessary for addressing oversmoothing on heterophilous graphs. It analyzes the theoretical and empirical implications of learnable versus fixed maps in Sheaf Neural Networks, offering insights into when learnable components help.

MPBMC: Multi-Property Bounded Model Checking with GNN-guided Clustering
GNN Graph Learning

MPBMC presents a framework for multi-property bounded model checking by clustering properties with GNN embeddings. The clustering aims to group related properties to be solved together, guided by the property cone of influence to improve verification efficiency.

Recurrent Graph Neural Networks and Arithmetic Circuits
GNN Graph Learning

We characterize the computational power of recurrent graph neural networks via recurrent arithmetic circuits, introducing memory gates to store data across iterations. This unifies recurrent GNNs with arithmetic circuit models and clarifies their expressive capabilities.

A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
GNN Graph Learning

We scalable model edge-wise dependencies in CopulaGNN for link sign prediction by modeling latent edge correlations with a Gaussian copula. The approach directly handles negative edges in signed graphs and improves predictive performance.

EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue
Knowledge Graph

EchoGuard presents an agentic AI framework with a knowledge-graph memory to detect manipulative communication in longitudinal dialogue. It uses a structured Log-Analyze-Reflect loop to track tactics like gaslighting and emotional coercion across interactions.

LLM-Grounded Explainability for Port Congestion Prediction via Temporal Graph Attention Networks
GNN Graph Learning LLM × Graph

AIS-TGNN couples a Temporal Graph Attention Network with an LLM reasoning module to produce port congestion predictions accompanied by faithful natural-language explanations, enabling evidence-based interpretability for operational decisions.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
GNN Graph Learning

From Spark to Fire examines error cascades in LLM-based multi-agent collaboration, showing how small inaccuracies can propagate into system-level false consensus. It proposes protections to trace and mitigate cascading errors without heavily restructuring collaboration.

GEM-TFL: Bridging Weak and Full Supervision for Forgery Localization through EM-Guided Decomposition and Temporal Refinement
Knowledge Graph LLM × Graph Graph Learning

GEM-TFL bridges weak and full supervision for temporal forgery localization by EM-guided decomposition and temporal refinement, addressing label scarcity and misalignment between training objectives and inference goals.

RoboPARA: Dual-Arm Robot Planning with Parallel Allocation and Recomposition Across Tasks
Knowledge Graph Graph Learning

RoboPARA introduces an LLM-driven dual-arm planning framework with a two-stage process: dependency-graph-based planning candidate generation and parallel allocation and recomposition across tasks for enhanced productivity.

Give Users the Wheel: Towards Promptable Recommendation Paradigm
Graph Learning

Give Users the Wheel argues for a promptable recommendation paradigm where explicit user intent expressed via prompts guides recommendations, aiming to combine the interpretability and flexibility of LLMs with the efficiency of fast recommenders.

Core-based Hierarchies for Efficient GraphRAG
Graph Learning LLM × Graph

Core-based Hierarchies for Efficient GraphRAG proposes organizing documents in GraphRAG by core-based hierarchies rather than Leiden clustering, enabling better global sensemaking on sparse knowledge graphs.