← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 28 papers for 2026-06-05

In-Context Graphical Inference
Graph Theory

This paper introduces In-Context Graphical Inference (ICG-I), an autoregressive Graph Transformer designed to preserve the sequential elimination structure used in exact marginal inference. It argues that the traditional exactness-vs-scalability trade-off arises from a misaligned inductive bias and proposes ICG-I to unify accuracy with scalable inference in discrete graphical models. The approach targets marginal inference on high-treewidth graphs where iterative methods struggle on frustrated topologies.

Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning
GNN Graph Learning

Graph Cascades introduces a mesoscopic rewiring strategy for Graph Neural Networks and Graph Transformers. Using contagion-based diffusion, it constructs an auxiliary graph where node pairs reinforced by multi-hop signals are promoted to direct neighbors, enabling better capture of intermediate-scale structure in linear time. The authors also provide theoretical conditions under which reinforcement-based rewiring improves performance.

Graph Set Transformer
GNN Graph Learning

The Graph Set Transformer (GST) learns on sets of graphs by interleaving node-level feature propagation with cross-graph contextual modelling at every layer. Unlike prior approaches that require pre-encoded graph embeddings, GST fuses local graph structure and set-wide context continuously to enable joint reasoning over a collection of graphs.

SpliceBind: Isoform-Aware Prediction of Binding Pocket Druggability
GNN Graph Learning

SpliceBind presents a graph neural network framework for isoform-aware prediction of binding-pocket druggability, enabling comparisons across splice variants. It improves predictive accuracy (AUROC) relative to a state-of-the-art baseline and analyzes when structural methods succeed or fail across six clinically validated variants.

Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks
GNN Graph Learning

DegradoMap introduces a graph neural network that predicts PROTAC-mediated degradability from protein structure and E3 ligase identity alone, without requiring the full PROTAC molecule. It encodes biophysical priors to guide the predictions and targets target selection at an early stage.

Bayesian Membership Privacy for Graph Neural Networks
GNN Graph Learning

Bayesian Membership Privacy (BMP) provides a sampling-aware formulation of node-level membership privacy for Graph Neural Networks, incorporating node-dependent priors and treating graph sampling probabilities as part of the privacy analysis. The framework advances privacy guarantees by accounting for graph structure and stochastic training.

EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning
Graph Learning

EpiFormer uses geometric deep learning to predict antigen–antibody epitopes by jointly modeling antigen and antibody structures. It addresses limitations of chain-wise antibody encoding and severe class imbalance, capturing co-dependent structural features that define binding interfaces.

HYolo: An Intelligent IoT-Based Object Detection System Using Hypergraph Learning
Graph Learning

HYolo integrates hypergraph learning into the YOLO object detector to model high-order contextual relationships among objects and contextual features in IoT settings. Experiments on COCO show significant performance gains.

Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction
GNN Graph Learning

Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction introduces ICGNN, which leverages graph structure to detect and correct mislabeled nodes by identifying contradictions in influence, improving robustness to noisy labels.

Fixed Aggregation Features Can Rival GNNs
GNN Graph Learning

Fixed Aggregation Features (FAFs) offer a training-free approach that converts graph learning into tabular problems. By computing FAFs and training simple MLPs, this method rivals or even surpasses many state-of-the-art GNNs across 14 benchmarks.

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

What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A study with Tabula RASA investigates four independently removable components (sparse adjacency masking, edge-type biases, query scaling, value gating) to isolate their impact. The striking finding is that sparse adjacency masking accounts for most of the improvement, while other components contribute modestly.

Minimizing the Hidden Cost of Scales: Graph-Guided Ultra-Low-Bit Quantization for Large Language Models
Graph Learning

SAGE-PTQ (Saliency-Aware Graph-guided Efficient PTQ) proposes an ultra-low-bit post-training quantization framework for LLMs that minimizes hidden scaling costs by separating salient and unsalient weights using distributional statistics and modeling unsalient weights as a sparse graph.

Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs
Graph Learning Knowledge Graph

Beyond Vector Similarity analyzes graph-augmented retrieval for industrial knowledge graphs by comparing eight retrieval architectures on a 46-node, 64-edge KG. It shows that five query classes are structurally unreachable by vector-only retrieval, supporting an operator vocabulary thesis that graph computation is necessary for structural queries.

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
Graph Learning

Memory is Reconstructed, Not Retrieved introduces MRAgent, a framework that combines an associative memory graph with active memory reconstruction. Memory is stored as a Cue–Tag–Content graph with semantic bridges to enable dynamic memory access during reasoning rather than static retrieval.

TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management
Graph Learning

TokenMizer provides a graph-structured session memory system to manage long-horizon LLM contexts. It models the session history as a graph-based memory in a proxy system to preserve structured information beyond the Maximum Effective Context Window.

CausalPOI: Spatio-Temporal Graph-Based Causal Modeling for Cold-Start POI Check-in Forecasting
GNN Graph Learning

CausalPOI introduces spatio-temporal graph-based causal modeling for cold-start POI check-in forecasting, aiming to capture functional dependencies and effects of urban interventions beyond simple proximity correlations.

HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tracking in UAV Aerial Imagery
GNN Graph Learning

HDST-GNN proposes a heterogeneous dynamic spatiotemporal GNN for multi-object tracking in UAV imagery, with altitude-adaptive edge construction and handling heterogeneous lifecycle states of detections, active tracklets, and lost targets.

Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability
GNN

Beyond Soft Masks introduces a Hard-Perturbation Mixup Explainer that improves robustness of GNN explanations by extending mixup ideas from soft subgraphs to hard perturbations.

Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Graph Learning

Reducing Hallucinations in Complex Question Answering proposes a simple graph-based Retrieval-Augmented Generation (RAG) approach to reduce hallucinations in complex QA tasks, providing a long-version discussion of the method.

AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling
GNN Graph Learning

AttackPathGNN reframes Solidity vulnerability detection as reasoning over explicit attack paths using state-interference graphs and conjunction pooling, distinguishing it from prior GNN detectors through architectural choices.

Harnessing Structural Context for Entity Alignment Foundation Models
Knowledge Graph Graph Learning

The paper analyzes how entity alignment foundation models underutilize structural context, causing weak cross-KG interaction during encoding and overreliance on coarse similarity in ranking. It proposes ContextEA to inject richer structural context into encoding and apply structure-aware scoring to improve alignment across unseen KG pairs.

Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation
Graph Learning

This work tackles cold-start item recommendation with an asymmetric graph architecture designed for production constraints. New content receives standalone embeddings for retrieval, and the model also generates device-appropriate embeddings for approximate nearest-neighbor retrieval, bridging semantic and collaborative signals efficiently.

Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
Knowledge Graph Graph Learning

The paper shows how diffusion models can generate graph-like logical rules for knowledge graph reasoning, capturing complex patterns such as cycles and branches beyond simple chains. This approach addresses the combinatorial explosion of rule search by learning generative graph rules that improve reasoning efficiency.

A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
Graph Learning

Introducing A2RAG, Adaptive Agentic Graph Retrieval for cost-aware and reliable reasoning, which addresses mixed-difficulty workloads and extraction loss in Graph-RAG. By using adaptive retrieval and agentic evidence routing, it preserves fine-grained qualifiers from source text and improves retrieval efficiency and reliability.

PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis
GNN Graph Learning

This work provides PAC-Bayesian, margin-based robust generalization analysis for message-passing GNNs under adversarial perturbations, highlighting sensitivity to weight perturbations and offering data-dependent bounds. It extends robustness analysis beyond isotropic Gaussian posteriors and informs robust training strategies.

End-to-End Subgraph Detection with GraphDETR
GNN Graph Learning

GraphDETR reframes subgraph detection as a set prediction problem, using a GNN encoder for the target subgraph and a DETR-like, bipartite-matching decoder to predict instances end-to-end, avoiding combinatorial searches inherent in traditional methods.

Edge-Aware Curvature Modeling for Graph Understanding in Large Language Models
LLM × Graph Graph Learning

The paper presents Edge-Aware Curvature Modeling to enhance graph understanding in LLMs by incorporating edge-level information into the graph-text alignment. This edge-centric view improves information propagation across views and strengthens cross-modal reasoning.

WebKnoGraph: GNN-Powered Internal Linking
GNN Graph Learning

WebKnoGraph is an open-source framework for evaluating internal linking strategies on website crawls with GNNs. It models a website as a directed graph and enables offline evaluation of candidate links before deployment to assess effects on authority and semantic coherence.