← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 66 papers for 2026-05-12

Path-Based Gradient Boosting for Graph-Level Prediction
Graph Learning

PathBoost introduces a gradient-boosting framework that learns discriminative path-based features directly from graphs for graph-level classification and regression. It extends prior work with a logistic loss for binary classification, a prefix-based decomposition to incorporate multiple node and edge attributes into the path feature space, and automatic anchor selection to improve feature construction.

Generalized Category Discovery in Federated Graph Learning
Graph Learning

Federated Graph Generalized Category Discovery (FGGCD) enables discovering novel categories across decentralized graph clients while preserving knowledge of known categories. The method targets the open-world setting in federated graph learning by tackling cross-client representation alignment and the incremental integration of new categories without sharing raw data.

Efficient Prompt Learning for Traffic Forecasting
GNN Graph Learning

Efficient Prompt Learning for Traffic Forecasting proposes a prompt-based adaptation framework for spatio-temporal graph neural networks to improve generalization under distribution shifts with reduced fine-tuning. By using trainable prompts, the model remains robust across varying traffic regimes and locations.

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
GNN

PRAETORIAN targets GNN backdoors by focusing on the intrinsic requirements of effective backdoors rather than surface cues. It observes that flipping a victim node's prediction requires substantial influence and that attackers tend to inject many trigger nodes, guiding robust defenses against adaptive attacks. The method analyzes internal correlations and external influences to detect and mitigate backdoors.

Graph Computation Meets Circuit Algebra: A Task-Aligned Analysis of Graph Neural Networks for Electronic Design Automation
GNN Graph Learning

Graph Computation Meets Circuit Algebra argues that successful GNNs for electronic design automation should align their propagation, aggregation, and supervision with the native algebra of the task. For example, static timing analysis maps to max-plus/min-plus recurrences on DAGs, while placement relies on hypergraph wirelength and density penalties, guiding task-aware differentiable solvers.

GNN for Structural Displacement Prediction
GNN Graph Learning

GNN for Structural Displacement Prediction presents a data-driven framework that models structural systems as graphs with joints as nodes to predict displacements under external loading. It aims to replace or augment FEM with fast, real-time predictions for structural health monitoring, balancing accuracy and efficiency.

Structure-Centric Graph Foundation Model via Geometric Bases
Graph Learning

Structure-Centric Graph Foundation Models (SCGFM) treat topology as the primary transferable knowledge and model graphs as metric measure spaces with learnable geometric bases that define a shared structural coordinate system. Graphs are aligned to these bases via Gromov-Wasserstein distances, yielding structure-aligned latent representations that transfer across domains.

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning
GNN Graph Learning

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning proposes a structural pruning method for SO(3) equivariant GNNs to reduce computational cost while preserving accuracy in atomistic simulations. Pruning is performed along channels and tensor orders to achieve efficient, scalable models.

Machine Learning-Based Graph Simplification for Symbolic Accelerators
Graph Learning

AutoSlim is a machine learning-based framework that prunes automata graphs for hardware accelerators by leveraging features from prior executions and a Random Forest classifier to identify low-impact nodes and edges. The data-driven pruning reduces memory usage and accelerates runtimes without sacrificing performance.

PACT: Peak-Aware Cross-Attention Graph Transformers for Efficient Storm-Surge Emulation
Graph Learning

PACT (Peak-Aware Cross-Attention Graph Transformer) delivers an efficient storm-surge emulator by encoding each forcing patch as a graph with GraphSAGE and using a learned station query to aggregate information through cross-attention. The model achieves accurate, fast predictions suitable for ensemble hazard assessments.

Hierarchical Attention-based Graph Neural Network with Relevance-driven Pruning
GNN Graph Learning

Hierarchical Attention-based Heterogeneous GNN (HA-HeteroGNN) addresses interpretability and efficiency by a two-tier attention mechanism across 16 node types and 18 edge types, enabling per-node relevance-based pruning. The framework provides an explainability-to-pruning pipeline for scalable heterogeneous graph reasoning.

RAwR: Role-Aware Rewiring via Approximate Equitable Partition
GNN

RAwR (Role-Aware Rewiring via Approximate Equitable Partition) augments inputs with a quotient graph from approximate equitable partition to alleviate oversquashing and enable long-range interactions. The rewiring improves information flow in graphs with bottlenecks, while maintaining scalable computation.

CTQWformer: A CTQW-based Transformer for Graph Classification
GNN Graph Learning

CTQWformer fuses continuous-time quantum walks (CTQW) with a Transformer by using a trainable Hamiltonian to blend graph topology and node features. This physically grounded approach models quantum walk dynamics to capture rich global dependencies for graph classification.

End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
GNN Graph Learning

End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor presents the first integrated FPGA implementation that combines a Neuromorphic Auditory Sensor (NAS) and a GNN for keyword spotting, enabling on-device processing with sparse event-based data.

ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics
GNN Graph Learning

ChaosNetBench provides a synthetic Chaos dynamics–based benchmark for spatio-temporal GNNs, enabling evaluation across controlled chaotic regimes. It supports comparisons of architectures under diverse dynamical conditions beyond real-world datasets.

UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
Graph Learning

UFO is a unified flow-oriented framework for robust continual graph learning that handles both catastrophic forgetting and noise in newly arriving graph portions. It integrates flow-based mechanisms to maintain stable learning on evolving graphs.

Learning Graph Foundation Models on Riemannian Graph-of-Graphs
Graph Learning

Learning Graph Foundation Models on Riemannian Graph-of-Graphs (R-GFM) treats structural scale as a first-class concept using a Riemannian GoG representation, enabling scale-aware transfer across graph domains and mitigating scale mismatch from fixed-hop subgraph sampling.

Anchor-guided Hypergraph Condensation with Dual-level Discrimination
Graph Learning

Anchor-guided Hypergraph Condensation with Dual-level Discrimination distills large hypergraphs into compact synthetic ones. It uses anchor-guided condensation with dual-level discrimination to preserve both structural fidelity and discriminative features, jointly optimizing the structure generator and condensed features.

One-Step Graph-Structured Neural Flows for Irregular Multivariate Time Series Classification
Graph Learning

One-Step Graph-Structured Neural Flows (GSNF) model irregular multivariate time series with a single mapping that captures inter-variable interactions. It addresses the limitations of treating variables independently by using graph-structured neural flows to model dependencies and improve classification.

Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
LLM × Graph Graph Learning

Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning introduces Graph Transformer Language Model (GTLM), a pretrained LLM architecture that natively processes graph topologies to alleviate the bottleneck of compressing graphs into single tokens. GTLM enables joint text and structure reasoning without heavy pipelines.

Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
Knowledge Graph Graph Learning

This work shows that principled relation operators in knowledge graph embeddings must satisfy linearity, trace preservation, and complete positivity, which together imply a Kraus channel structure via the Kraus representation theorem. The completeness constraint is shown to be equivalent to these axioms, offering a foundational alternative to externally imposed design choices. By recasting relations as Kraus channels, the authors unify and constrain common KG embedding operators while enabling principled generalization.

CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs
Knowledge Graph Graph Learning

CMKL introduces modality-aware continual learning for evolving biomedical knowledge graphs. It leverages multimodal signals and targeted regularization to adapt to changing graph structures while avoiding uniform treatment across modalities. Experiments show improved accuracy and robustness over baselines on evolving KGs.

It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction
GNN Graph Learning

We propose topology-aware structural graph encoding that preserves chain-scale morphology in polymers, addressing the limits of using only repeat-unit graphs. The encoding captures how chain distribution influences properties and improves predictive performance under small data regimes. This leads to more accurate polymer property predictions.

On Improving Graph Neural Networks for QSAR by Pre-training on Extended-Connectivity Fingerprints
GNN Graph Learning

We propose a general pre-training strategy for QSAR: train GNNs to predict Extended-Connectivity Fingerprints (ECFP). This pre-training improves downstream QSAR performance, particularly under out-of-distribution splits, with five of six Biogen benchmarks showing statistical significance.

Belief or Circuitry? Causal Evidence for In-Context Graph Learning
Graph Learning

We study in-context graph learning in large language models with a toy graph random-walk over two competing structures. The results indicate that neither global topology nor local transitions alone suffice. PCA of intermediate representations reveals both topologies are encoded in orthogonal subspaces at certain mixture ratios, suggesting a mixed mechanism.

Attention-based graph neural networks: a survey
GNN Graph Learning

This survey reviews attention-based GNNs, outlining how attention helps select discriminative features and filter noise. It provides a taxonomy, discusses design choices, datasets, evaluation practices, and practical guidance, and highlights gaps and directions for future work.

Enabling Structure-Only Initialization and Out-of-Distribution Generalization in GNN-based Molecular Dynamics Simulators
GNN Graph Learning

We address the dependence on temporal context by enabling structure-only initialization for GNN-based MD simulators. This init uses static structural information, enabling better out-of-distribution generalization while preserving differentiability for inverse design tasks. The results show improved generalization and potential benefits for design workflows.

PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
Knowledge Graph Graph Learning

PrimeKG-CL introduces a continual learning benchmark for evolving biomedical KGs, assembled from nine authoritative sources with realistic update patterns. It captures asynchronous growth, edge deprecation, and modality changes to stress CGL methods. The paper provides baselines and evaluation protocols.

Bridging Sequence and Graph Structure for Epigenetic Age Prediction
Graph Learning

We propose a unified framework that jointly models co-methylation graph structure with site-specific DNA sequence context to predict epigenetic age. This integration improves accuracy over methods using only sequence or graph information and supports more reliable age estimations.

Reconfigurable Computing Challenge: Real-Time Graph Neural Networks for Online Event Selection in Big Science
GNN Graph Learning

We demonstrate end-to-end real-time deployment of a dynamic GNN for online event selection in a collider trigger, implemented on FPGA-based hardware (Versal VCK190). The work addresses latency and throughput constraints with hardware-software co-design and reports practical viability for big-science triggers.

Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
GNN Graph Learning

We propose an explanation-based detection framework for backdoored GNNs that combines multiple explanation-derived metrics rather than relying on a single indicator. The approach improves robustness against diverse backdoor strategies and outperforms prior single-metric detectors.

Explaining Graph Neural Networks for Node Similarity on Graphs
GNN Graph Learning

We explore explainable node similarity by augmenting GNN-based similarity with explanations that attribute which substructures or features drive the similarity. The framework yields human-interpretable reasons for why nodes are considered similar.

Structural Alignment Improves Graph Test-Time Adaptation
Graph Learning

We introduce Test-Time Structural Alignment (TSA), a Graph Test-Time Adaptation method that aligns a pretrained GNN to the target graph structure at test time, enabling adaptation without retraining. This yields better performance under distribution shifts.

Toward General and Robust LLM-enhanced Text-attributed Graph Learning
Graph Learning LLM × Graph

This work discusses LLM-enhanced text-attributed graph learning and proposes a unified framework to systematize diverse optimization perspectives when using LLMs to generate graph descriptions. It also outlines key challenges and practical guidelines.

Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices
GNN Graph Learning

We propose Local-UID feature augmentation for GNNs solving ILPs within Learning-to-Optimize, avoiding issues with globally unique IDs. The approach preserves expressiveness while reducing spurious correlations, improving generalization.

GraphBench: Next-generation graph learning benchmarking
Graph Learning

GraphBench provides a comprehensive benchmark for graph learning with diverse datasets and tasks, standardized evaluation protocols, and support for graph foundation models. It aims to improve reproducibility and enable thorough evaluation beyond narrow benchmarks.

DUALFloodGNN: Physics-informed Graph Neural Network for Operational Flood Modeling
GNN Graph Learning

DUALFloodGNN integrates data-driven GNN predictions with physical constraints to improve realtime flood modeling. The physics-informed approach yields faster, more reliable forecasts useful for operational flood management.

Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
GNN Graph Learning

We formulate adversarial attacks guided by Optimal Transport on GNN-based bot detectors, considering domain and temporal constraints. The results show attackers can degrade detection under realistic conditions, underscoring the need for robust defenses.

What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA
Knowledge Graph Graph Learning

We perform controlled ablations of a minimal transformer modification with four components—sparse adjacency masking, edge-type biases, query scaling, and value gating—to isolate their contributions. We find sparse adjacency masking accounts for the majority of improvement in three-hop and other benchmarks, while the other components contribute less.

Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
GNN

We show that pairwise message passing limits learning for multi-agent pathfinding. We propose Hypergraph Neural Networks to capture higher-order interactions among agents, and experiments show improved coordination and fewer collisions compared with pairwise GNN baselines.

LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs
GNN Graph Learning LLM × Graph

This paper reframes text-rich graphs by treating node text as the primary medium through which structure is expressed, not just a static attribute. It argues that existing workflows compress text into embeddings before reasoning, creating an information bottleneck, and proposes the RAMP framework to rethink message passing to leverage raw text for graph reasoning.

Inductive Entity Representations from Text via Link Prediction
Knowledge Graph Graph Learning

Knowledge graphs are often incomplete, and textual descriptions offer rich information for entities. This work learns inductive entity representations from text to support link prediction and examines generalization to unseen entities.

Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation
Knowledge Graph Graph Learning

The paper questions the assumption that neural CQA models generalize beyond explicit graph structure by comparing them with a training-free query relaxation strategy that relaxes constraints and counts paths. Across multiple datasets, the results illuminate when neural methods truly extrapolate and when simple relaxation suffices.

SKG-VLA: Scene Knowledge Graph Priors for Structured Scene Semantics and Multimodal Reasoning for Decision Making
Knowledge Graph Graph Learning

We introduce SKG-VLA for multimodal decision making by modeling scene structure and priors in a knowledge graph to integrate heterogeneous evidence (narratives, screenshots, metadata, policies). The approach leverages explicit scene structure and cross-evidence dependencies to improve decision quality.

EpiGraph: A Knowledge Graph and Benchmark for Evidence-Intensive Reasoning in Epilepsy
Knowledge Graph Graph Learning

EpiGraph constructs a large epilepsy knowledge graph and benchmark to support evidence-intensive clinical reasoning, integrating 48,166 peer-reviewed papers and seven clinical resources into 24,324 entities and 32,009 evidence-grounded triplets.

LLM-Guided Monte Carlo Tree Search over Knowledge Graphs: Composing Mechanistic Explanations for Drug-Disease Pairs
Knowledge Graph Graph Learning LLM × Graph

TESSERA is a 3-part neuro-symbolic framework that uses LLMs to provide local guidance for Monte Carlo Tree Search over knowledge graphs, enabling the composition of mechanistic explanations for drug–disease pairs.

HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
Graph Learning

HAGE introduces a weighted, multi-relational memory framework where memory retrieval is treated as sequential, query-conditioned traversal over a unified relational memory graph. This design allows varying relation strengths and confidence to influence retrieval for agentic LLM systems.

MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs
Knowledge Graph Graph Learning

MAGE externalizes self-knowledge of multiple agents into a four-subgraph co-evolutionary knowledge graph, supporting what each agent learns and how it preserves knowledge across iterations. The framework enables self-evolving agents to coordinate and reason with a frozen backbone at inference.

SLASH the Sink: Sharpening Structural Attention Inside LLMs
Graph Learning LLM × Graph

SLASH investigates how LLMs internalize graph structure, finding a sawtooth pattern in attention that indicates spontaneous topology reconstruction, offering a path to sharpen internal structural attention without external adapters.

PathISE: Learning Informative Path Supervision for Knowledge Graph Question Answering
Knowledge Graph Graph Learning

PathISE proposes learning informative path supervision for KGQA, reducing the need for costly intermediate annotations by guiding evidence retrieval along question-relevant KG paths and subgraphs, enabling better grounding of LLMs.

Crystal Fractional Graph Neural Network for Energy Prediction of High-Entropy Alloys
GNN

Crystal Fractional Graph Neural Network (GNN) for energy prediction in high-entropy alloys combines local crystal environments with global composition using graph attention to capture both intra-site interactions and overall alloy composition.

From Historical Tabular Image to Knowledge Graphs: A Provenance-Aware Modular Pipeline
Knowledge Graph

This paper presents a provenance-aware modular pipeline to convert historical handwritten tabular images into knowledge graphs, ensuring transparency, reproducibility, and trust by tracking each transformation step.

Multi-Level Graph Attention Network Contrastive Learning for Knowledge-Aware Recommendation
GNN Graph Learning Knowledge Graph

We propose a multi-level graph attention network with contrastive learning across multiple views to enhance knowledge-aware recommendations, addressing sparse labels, limited structure learning, and noisy KG entities.

ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
Graph Learning

ShadowMerge introduces a novel poisoning attack on graph-based agent memory by exploiting relation-channel conflicts, enabling an attacker to insert conflicting relations that later influence agent decisions.

HOME-KGQA: A Benchmark Dataset for Multimodal Knowledge Graph Question Answering on Household Daily Activities
Knowledge Graph Graph Learning

HOME-KGQA provides a benchmark dataset for multimodal knowledge graph question answering focused on household daily activities, addressing bias toward encyclopedic knowledge by offering household-relevant scenarios.

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning
Knowledge Graph

Oracle Poisoning defines attacks where adversaries corrupt knowledge graphs that AI agents query at runtime, demonstrating six scenarios on a large production code KG to weaponize agent reasoning.

MicroWorld: Empowering Multimodal Large Language Models to Bridge the Microscopic Domain Gap with Multimodal Attribute Graph
Graph Learning

MicroWorld builds a multimodal attributed property graph from scientific image-caption corpora and uses it to augment multimodal LLM reasoning at inference, bridging the microscopic domain gap without additional training data.

GraphReAct: Reasoning and Acting for Multi-step Graph Inference
Graph Learning

GraphReAct extends reasoning-acting frameworks to graphs by interleaving evidence retrieval from graphs with multi-step reasoning and actions, enabling dynamic, iterative graph inference with LLMs.

Watermarking Graph Neural Networks via Explanations for Ownership Protection
GNN Graph Learning

The paper proposes watermarking GNNs via explanations to protect ownership, addressing limitations of backdoor-based methods and avoiding data poisoning while embedding verifiable ownership signals.

ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
Graph Learning Knowledge Graph

ArchRAG introduces an attributed community-based hierarchical retrieval-Augmented Generation framework to improve relevance and efficiency in graph-based QA by organizing retrieval around graph communities.

TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
GNN Graph Learning

We propose TextBridgeGNN, a pre-trained graph neural network for cross-domain recommendation that uses text-guided transfer to bridge domain gaps. It addresses the non-transferability of ID embeddings across isolated domains and structural heterogeneity between heterogeneous interactions by aligning cross-domain semantics via textual information. This results in a more transferable recommender that can perform across domains and cold starts.

Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Graph Learning

We introduce Response-G1, a framework for proactive streaming video understanding that builds explicit scene graphs to align accumulated visual evidence with the query's expected response conditions. It performs three fine-tuning-free stages, including online query-guided scene graph generation from streaming clips and explicit alignment between evidence and response needs. This structured approach improves when-to-respond decisions during video unfolding.

GraphInstruct: A Progressive Benchmark for Diagnosing Capability Gaps in LLM Graph Generation
LLM × Graph

GraphInstruct presents a progressive benchmark to diagnose capability gaps in LLM-based graph generation. It evaluates instruction-following graph synthesis across diverse graph types and tasks, revealing where models struggle and guiding targeted improvements. It advances beyond pre-LLM graph-generation reviews by focusing on instruction adherence and practical prompting.

GraphNetz: Statistical Benchmarking of Graph Neural Networks with Paired Tests and Rank Aggregation
GNN Graph Learning

GraphNetz is a benchmarking framework for GNNs that emphasizes statistical reporting over raw accuracy tables. It provides confidence intervals, paired tests, multiple-comparison corrections, and rank aggregation to yield structured statistical comparisons across datasets, seeds, and models. The default output is a structured statistical report rather than a plain accuracy table.

Global-local Spatial-temporal Aware Graph Attention Network for Network Traffic Forecasting
GNN Graph Learning

Global-local Spatial-temporal Aware Graph Attention Network for Network Traffic Forecasting proposes a model that addresses limitations of predefined spatial adjacency by capturing global and local spatial dependencies and dynamic temporal patterns with graph attention. It yields improved accuracy and robustness in forecasting network traffic.

Toward Multi-Database Query Reasoning for Text2Cypher
LLM × Graph

Toward Multi-Database Query Reasoning for Text2Cypher discusses extending Text2Cypher from a single graph database to a multi-database setting, enabling queries across several independent graphs with varying schemas. It introduces mechanisms for database selection, schema alignment, and cross-graph Cypher query composition to enable seamless cross-domain data access.