Methods › Natural Language Processing › Transformers › EGT
Edge-augmented Graph Transformer
EGT
Introduced by Md Shamim Hussain et al. in Global Self-Attention as a Replacement for Graph Convolution
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Transformer neural networks have achieved state-of-the-art results for unstructured data such as text and images but their adoption for graph-structured data has been limited. This is partly due to the difficulty of incorporating complex structural information in the basic transformer framework. We propose a simple yet powerful extension to the transformer - residual edge channels. The resultant framework, which we call Edge-augmented Graph Transformer (EGT), can directly accept, process and output structural information as well as node information. It allows us to use global self-attention, the key element of transformers, directly for graphs and comes with the benefit of long-range interaction among nodes. Moreover, the edge channels allow the structural information to evolve from layer to layer, and prediction tasks on edges/links can be performed directly from the output embeddings of these channels. In addition, we introduce a generalized positional encoding scheme for graphs based on Singular Value Decomposition which can improve the performance of EGT. Our framework, which relies on global node feature aggregation, achieves better performance compared to Convolutional/Message-Passing Graph Neural Networks, which rely on local feature aggregation within a neighborhood. We verify the performance of EGT in a supervised learning setting on a wide range of experiments on benchmark datasets. Our findings indicate that convolutional aggregation is not an essential inductive bias for graphs and global self-attention can serve as a flexible and adaptive alternative.
Papers archive 2025-07-28
10 shown of 10, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Understanding the rift between update rules in Evolutionary Graph Theory: The intrinsic death rate drives star graphs from amplifying to suppressing natural selection 18 Jun 2025 · 0 repositories · arXiv:2506.15528
-
Serious Games: Human-AI Interaction, Evolution, and Coevolution 22 May 2025 · 0 repositories · arXiv:2505.16388
-
Kolmogorov-Arnold Networks and Evolutionary Game Theory for More Personalized Cancer Treatment 12 Jan 2025 · 0 repositories · arXiv:2501.07611
-
Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective 30 Nov 2024 · 1 repository · arXiv:2412.00542
-
Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts 22 Oct 2024 · 0 repositories · arXiv:2410.19852
-
Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification 25 May 2023 · 0 repositories · arXiv:2305.15773
-
Convergence analysis and acceleration of the smoothing methods for solving extensive-form games 20 Mar 2023 · 0 repositories · arXiv:2303.11046
-
Understanding Emergent Behaviours in Multi-Agent Systems with Evolutionary Game Theory 15 May 2022 · 0 repositories · arXiv:2205.07369
-
Explainable Artificial Intelligence for Exhaust Gas Temperature of Turbofan Engines 24 Mar 2022 · 0 repositories · arXiv:2203.13108
-
Global Self-Attention as a Replacement for Graph Convolution 7 Aug 2021 · 3 repositories · arXiv:2108.03348Syntology ran 0 of 4 samples · 4 unverified
Tasks archive 2025-07-28
18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections