No article text was recorded for this version.
quadratic attention complexity (global attention scalability)
Version 1 of 134 papers36 conceptsfrozen 2026-10-04
Papers in this version
- Blog: On the Global Self-attention Mechanism for Graph Convolutional Networks
- Blog: Learning from Historical Activations in Graph Neural Networks
- Blog: Multipole Graph Neural Operator for Parametric Partial Differential Equations
- Blog: Transformers over Directed Acyclic Graphs
- Blog: ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding
- Blog: Monotone Operator Theory-Inspired Message Passing for Learning Long-Range Interaction on Graphs
- Blog: Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification
- Blog: Matching Biomedical Ontologies via a Hybrid Graph Attention Network
- Blog: Forest-Based Graph Learning for Semi-Supervised Node Classification
- Blog: Relation-Aware Weighted Embedding for Heterogeneous Graphs
- Blog: Conditional Graph Information Bottleneck for Molecular Relational Learning
- Blog: A recipe for scalable attention-based ML potentials: unlocking long-range accuracy with all-to-all node attention
- Blog: Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion
- Blog: Understanding Virtual Nodes: Oversquashing and Node Heterogeneity
- Blog: ReHub: Linear Complexity Graph Transformers with Adaptive Hub-Spoke Reassignment
- Blog: Improving the Effective Receptive Field of Message-Passing Neural Networks
- Blog: Hgformer: Hyperbolic Graph Transformer for Collaborative Filtering
- Blog: ST-GRAT: A Novel Spatio-temporal Graph Attention Networks for Accurately Forecasting Dynamically Changing Road Speed
- Blog: Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
- Blog: GOAT: A Global Transformer on Large-scale Graphs
- Blog: GRAMA: Adaptive Graph Autoregressive Moving Average Models
- Blog: InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
- Blog: LoginMEA: Local-to-Global Interaction Network for Multi-modal Entity Alignment
- Blog: Towards Dynamic Message Passing on Graphs
- Blog: Primphormer: Efficient Graph Transformers with Primal Representations
- Blog: Gapformer: Graph Transformer with Graph Pooling for Node Classification
- Blog: Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
- Blog: Long Range Graph Benchmark
- Blog: Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
- Blog: Recurrent Distance Filtering for Graph Representation Learning
- Blog: Learning Contextualized Knowledge Structures for Commonsense Reasoning
- Blog: Improving Breadth-Wise Backpropagation in Graph Neural Networks Helps Learning Long-Range Dependencies
- Blog: Graph Representation Learning via Hard and Channel-Wise Attention Networks
- Blog: Attending to Graph Transformers
History & citation
Current · Permanent link
- This direction split from Efficient Global Information Propagation in Graphs (85% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_quadratic_attention_complexity_global_at_ac57844a,
title = {quadratic attention complexity (global attention scalability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/quadratic-attention-complexity-global-attention-scalability/rdr_ac57844ae1e34d92ae7bca702576120b},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_quadratic_attention_complexity_global_at_ac57844a_v1,
title = {quadratic attention complexity (global attention scalability)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/quadratic-attention-complexity-global-attention-scalability/rdr_ac57844ae1e34d92ae7bca702576120b/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}