Graph Transformer

Follow this topic Ask about this topic

Graph Transformers study how attention-based models can learn from nodes, edges, and other relationships while respecting graph structure. Common approaches add positional or structural encodings—such as Laplacian spectra, random walks, or graph distances—or use local, sparse, hierarchical, and relation-aware attention to control computation. They are applied to tasks including molecular prediction, temporal and relational graphs, scientific modeling, and graph generation, with evaluations spanning standard graph benchmarks and larger or shifted settings. A central tension is how to preserve useful structural biases and generalize across graph sizes while scaling attention; theory also indicates that global attention alone does not necessarily overcome the expressive limits of common graph architectures.

Latest papers

101 papers17 papers in the last four weeks, up 89% on the four weeks before. 0.1% of all new papers.

Graph Attention Based Prioritization of Disease Responsible Genes from Multimodal Alzheimer's Network
Mar 1, 2026Binon Teji, Subhajit Bandyopadhyay, Swarup RoyGenomics Multimodal Graph Learning
Network Reconstruction & Analysis Lab and Department of Computer Applications, Sikkim University, Sikkim, India, 737102 · Department of Computer Science & Engineering, Tezpur University, Assam, India, 784028
An Analysis of Role Semantics in Directed Dynamic Graph Modeling for Edge Classification
Feb 26, 2026Tyler Bonnet, Marek ReiGraph Representation Learning Self-Supervised Pre-Training
Imperial College London
Probing Graph Neural Network Activation Patterns Through Graph Topology
Feb 24, 2026Floriano Tori, Lorenzo Bini, Marco Sorbi +2Massive Activations Graph Transformer
Business Technology and Operations, Vrije Universiteit Brussels, Brussels, Belgium · Department of Computer Science, University of Geneva, Geneva, Switzerland · Research Institute for Statistics and Information Science, Geneva, Switzerland +1
VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention
Feb 23, 2026Jingbo Zhou, Jun Xia, Siyuan Li +11Graph Transformer Node Classification
Zhejiang University Hangzhou, Zhejiang, China · Westlake University Hangzhou, Zhejiang, China · Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China +4
AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation
Feb 19, 2026Rong Fu, Chunlei Meng, Shuo Yin +2Graph Neural Networks Graph Structure Learning
Independent Researcher
Context-aware Skin Cancer Epithelial Cell Classification with Scalable Graph Transformers
Feb 17, 2026Lucas Sancéré, Noémie Moreau, Katarzyna BozekComputational Pathology Oncology
Faculty of Mathematics and Natural Sciences, University of Cologne, Cologne, North Rhine-Westphalia, Germany · Institute for Biomedical Informatics, Faculty of Medicine and University Hospital Cologne, University of Cologne, North Rhine-Westphalia, Germany · Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital Cologne, University of Cologne, North Rhine-Westphalia, Germany +1
Size-Transferability of Graph Transformers with Convolutional Positional Encodings
Feb 16, 2026Javier Porras-Valenzuela, Zhiyang Wang, Teresa Shang +2Graph Positional Encoding Graph Transformer
Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA · Halıcıoğlu Data Science Institute, University of California San Diego, La Jolla, CA, USA
Joint Sensor Deployment and Physics-Informed Graph Transformer for Smart Grid Attack Detection
Feb 16, 2026Mariam Elnour, Mohammad AlShaikh Saleh, Rachad Atat +6Power Systems Physics-Informed GNNs
department of Electrical and Computer Engineering, Texas A&M University, College Station, TX 77840, USA · department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha, Qatar · department of Computer Science and Mathematics, Lebanese American University, Beirut 1102-2801, Lebanon +4
Plain Transformers are Surprisingly Powerful Link Predictors
Feb 2, 2026Quang Truong, Yu Song, Donald Loveland +4Transformer Graph Representation Learning
Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, USA. · Snap Inc., Bellevue, WA, USA.
Transformer-Based Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions
Nov 17, 2025Vidur Sinha, Muhammed Ustaomeroglu, Guannan QuCounterfactual Credit Assignment Graph Transformer
Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, USA
Rotary Position Encodings for Graphs
Sep 26, 2025Isaac Reid, Arijit Sehanobish, Cederik Höfs +7Graph Positional Encoding Rotary Positional Embeddings
University of Cambridge · Google DeepMind · Independent Researcher +3

Mar 1, 2026J/K move · Enter open · S save

Graph Attention Based Prioritization of Disease Responsible Genes from Multimodal Alzheimer's Network

Binon Teji, Subhajit Bandyopadhyay, Swarup Roy

Network Reconstruction & Analysis Lab and Department of Computer Applications, Sikkim University, Sikkim, India, 737102 · Department of Computer Science & Engineering, Tezpur University, Assam, India, 784028

Genomics Multimodal Graph Learning Alzheimer's Disease Graph Transformer

Open paper AskPDF arXiv

Prioritizing disease-associated genes is central to understanding the molecular mechanisms of complex disorders such as Alzheimer's disease (AD). Traditional network-based approaches rely on static centrality measures and often fail to capture cross-modal biological heterogeneity. We propose NETRA (Node Evaluation through Transformer-based Representation and Attention), a multimodal graph transformer framework that replaces heuristic centrality metrics with attention-driven relevance scoring. Using AD as a case study, gene regulatory networks are independently constructed from microarray, single-cell RNA-seq, and single-nucleus RNA-seq data. Random-walk sequences derived from these networks are used to train a BERT-based model for learning global gene embeddings, while modality-specific gene expression profiles are compressed using variational autoencoders. These representations are integrated with auxiliary biological networks, including protein-protein interactions, Gene Ontology semantic similarity, and diffusion-based gene similarity, into a unified multimodal graph. A graph transformer assigns NETRA scores that quantify gene relevance in a disease-specific and context-aware manner. Gene set enrichment analysis shows that NETRA achieves a normalized enrichment score of about 3.9 for the Alzheimer's disease pathway, substantially outperforming classical centrality measures and diffusion models. Top-ranked genes enrich multiple neurodegenerative pathways, recover a known late-onset AD susceptibility locus at chr12q13, and reveal conserved cross-disease gene modules. The framework preserves biologically realistic heavy-tailed network topology and is readily extensible to other complex disorders.