Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
super hub Canonical reference
Graph Attention Networks
Canonical reference. 70% of citing Pith papers cite this work as background.
205
Pith papers citing it
Background
70% of classified citations
abstract
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).
hub tools
citation-role summary
background 15
method 3
baseline 2
citation-polarity summary
claims ledger
- abstract We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key
authors
co-cited works
representative citing papers
PromptGNN-sim uses GAT-based semantically aware neighborhood selection and structure-aware LLM prompts with bi-directional contrastive alignment to outperform prior GNN, LLM, and fusion methods on text-attributed graph datasets.
Proposes equation-grounded taxonomy (unexpected AIS activity, route deviation, close approach) and LLM-guided synthesis pipeline to generate timestamp-labeled anomalies for evaluating maritime detection models.
QuADA-GS learns to predict local complexity-driven Gaussian densification from low-resolution inputs and uses Hierarchical Pointer Convolution for efficient arbitrary-scale super-resolution.
GILP trains a parameterized backbone for valid actions and state predictions, then uses a consistency gate with LLM drafts to reduce hallucinated-state rate from 0.176 to 0.035 on GPT-4o-mini while raising success from 0.668 to 0.838.
GraphNPE recovers a significantly lower central density for Boötes I consistent with a core while Draco remains marginally cuspy, and demonstrates that higher-order velocity moments reduce bias in dynamical modeling.
A timestamp-aware spatio-temporal graph contrastive learning model for network intrusion detection outperforms other self-supervised methods on four datasets while matching supervised GNN performance.
SelfTICA reformulates collective-variable discovery as contrastive dynamical representation learning on time-lagged data, decoupling feature learning from slow-mode extraction to produce reusable collective variables from limited or biased trajectories.
Introduces Hypergraph U-Nets with PHPool and PHUnpool operators derived from hierarchical clustering dendrograms for hypergraph reconstruction, classification, and anomaly detection.
An agentic multi-fidelity learning method corrects numerical artifacts in GW-BSE excited-state calculations for 2D bilayers and improves quasiparticle gaps and exciton binding energies.
Benchmark of BINN, GraphPath, and PATH on 2622 TCGA patients shows PATH best for targeted therapy, BINN for survival, none useful for radiation, with GraphPath at 0.92 AUROC on prostate targeted therapy.
EpiFormer improves epitope prediction F1 score by over 40% via early-fusion cross-attention in GNN layers and sparsity-aware objectives, while recovering known biology as emergent behavior.
LightGBM models on citation and diversity features predict exogenous diffusion of quantum computing concepts with R² up to 0.78 while endogenous reinforcement remains largely unpredictable after growth controls, with replications in other fields.
AbstainGNN is a framework that jointly models prediction and abstention in GNNs for graph classification, using a PAC-Bayesian-derived unified objective and two-stage training to achieve better accuracy at given rejection rates than prior abstention methods.
ContrastAD achieves highest mean F1 on all five MTS benchmarks and highest AUC on three by building DTW-based sparse graph snapshots and contrasting divergent pairs with a stable anchor instead of enforcing invariance.
Gaussian Sheaf Neural Networks derive a sheaf Laplacian for Gaussian node features on graphs to preserve their geometric structure during message passing.
NeighborDiv detects graph anomalies via variance of inter-neighbor feature similarities under a new Neighbor-to-Neighbor Diversity Paradigm, achieving SOTA results with zero volatility in zero-shot cross-domain settings.
Contrastive Message Passing lets GNNs apply similarity-preserving transforms to positive edges and dissimilarity-inducing transforms to negative edges via soft positive semidefinite constraints on weights, yielding gains in low-label high-homophily regimes.
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
TopoU-Net is a rank-path U-Net for combinatorial complexes that encodes by lifting cochains upward along incidences, decodes by transporting downward, and merges via skip connections at matched ranks.
CTQWformer fuses continuous-time quantum walks into a graph transformer and recurrent module to outperform standard GNNs and graph kernels on classification benchmarks.
SoftBlobGIN combines ESM-2 representations with protein contact graphs via a lightweight GNN and differentiable substructure pooling to achieve 92.8% accuracy on enzyme classification, raise binding-site AUROC to 0.983, and generate auditable structural explanations without retraining the language模型
SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
Graphlets mined as structural tokens improve zero-shot inductive and transductive link prediction in knowledge graph foundation models across 51 diverse graphs.
citing papers explorer
-
A document is worth a structured record: Principled inductive bias design for document recognition
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
-
Learning to Adaptively Allocate Gaussians for Arbitrary-Scale Image Super-Resolution
QuADA-GS learns to predict local complexity-driven Gaussian densification from low-resolution inputs and uses Hierarchical Pointer Convolution for efficient arbitrary-scale super-resolution.
-
Hierarchical Mesh Transformers with Topology-Guided Pretraining for Morphometric Analysis of Brain Structures
A hierarchical mesh transformer using topology-guided pretraining on simplicial complexes achieves state-of-the-art results on Alzheimer's classification, amyloid prediction, and focal cortical dysplasia detection from brain meshes.
-
EndoVGGT: GNN-Enhanced Depth Estimation for Surgical 3D Reconstruction
EndoVGGT uses a dynamic DeGAT graph attention module to improve depth estimation and non-rigid 3D reconstruction in surgery, reporting 24.6% PSNR and 9.1% SSIM gains on SCARED with zero-shot generalization to new domains.
-
GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
GRAPE augments prototype medical image classifiers with graph attention for co-occurrence, a mismatch safety check, and open-vocabulary anchoring to support incremental addition of findings from single examples.
-
fMRI-Diffusion: Generating fMRI Time Series Via a Temporal Transformer Diffusion Model for Major Depressive Disorder Diagnosis
fMRI-Diffusion generates synthetic ROI-level fMRI time series via a temporal transformer diffusion model with supervised pretraining, improving MDD diagnostic accuracy by up to 3.7 percentage points over prior FC-matrix synthesis methods on the REST-meta-MDD dataset.
-
Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
SkyPart achieves state-of-the-art single-pass cross-view geo-localization on SUES-200, University-1652, and DenseUAV by using prototype-based part discovery, altitude-conditioned modulation, and Kendall-weighted loss, with widening gains under weather corruptions.
-
Region-Affinity Attention for Whole-Slide Breast Cancer Classification in Deep Ultraviolet Imaging
A novel Region-Affinity Attention mechanism classifies breast cancer on whole deep ultraviolet slides, achieving 92.67% accuracy and 95.97% AUC on 136 samples while outperforming standard attention methods.
-
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
DG-STA builds dynamic graphs from hand skeletons, applies spatial-temporal self-attention to learn features, and uses a mask to cut cost by 99%, outperforming prior methods on DHG-14/28 and SHREC'17.
-
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.
-
Attention U-Net: Learning Where to Look for the Pancreas
Attention gates added to U-Net automatically focus on target organs in CT images and improve segmentation performance on abdominal datasets.
-
Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement
The paper presents a case-aware multimodal knowledge graph approach for medical image classification that retrieves similar cases, propagates knowledge via graph attention, and refines predictions with reliability estimates.
-
Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
Social-BiGAT is a graph-based generative adversarial network using GAT for social interaction features and Bicycle-GAN for multimodal outputs that reports state-of-the-art results on pedestrian trajectory forecasting benchmarks.
-
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight integrates a Molecular Topology Module and Molecular Grounding Module into VLMs to enhance molecular image understanding and claims to outperform prior models on chemical visual tasks.
-
A Dual Cross-Attention Graph Learning Framework For Multimodal MRI-Based Major Depressive Disorder Detection
Dual cross-attention fusion of sMRI and rs-fMRI data achieves 84.71% accuracy in MDD detection on the REST-meta-MDD dataset, outperforming concatenation on functional atlases.
-
Bridging the Dimensionality Gap: A Taxonomy and Survey of 2D Vision Model Adaptation for 3D Analysis
The paper offers a taxonomy of 2D-to-3D adaptation strategies divided into data-centric projection, architecture-centric 3D networks, and hybrid methods that combine both.
-
Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
-
PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
PH-GCN constructs a hierarchical graph of person parts and performs local/global feature learning via message passing in an end-to-end network for person re-identification.