{"url":"/method/egt","slug":"egt","name":"EGT","full_name":"Edge-augmented Graph Transformer","full_name_withheld":false,"description_markdown":"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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Global Self-Attention as a Replacement for Graph Convolution","paper":"/paper/edge-augmented-graph-transformers-global-self","first_author":"Md Shamim Hussain","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/edge-augmented-graph-transformers-global-self"},"source":{"url":"https://arxiv.org/abs/2108.03348v3","title":"Global Self-Attention as a Replacement for Graph Convolution","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":10,"archive_num_papers":10,"papers_newest_first":[{"paper":null,"title":"Understanding the rift between update rules in Evolutionary Graph Theory: The intrinsic death rate drives star graphs from amplifying to suppressing natural selection","date":"2025-06-18","arxiv_id":"2506.15528","n_code_links":0,"syntology":null},{"paper":null,"title":"Serious Games: Human-AI Interaction, Evolution, and Coevolution","date":"2025-05-22","arxiv_id":"2505.16388","n_code_links":0,"syntology":null},{"paper":null,"title":"Kolmogorov-Arnold Networks and Evolutionary Game Theory for More Personalized Cancer Treatment","date":"2025-01-12","arxiv_id":"2501.07611","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-generalizability-and","title":"Rethinking Generalizability and Discriminability of Self-Supervised Learning from Evolutionary Game Theory Perspective","date":"2024-11-30","arxiv_id":"2412.00542","n_code_links":1,"syntology":null},{"paper":null,"title":"Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts","date":"2024-10-22","arxiv_id":"2410.19852","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification","date":"2023-05-25","arxiv_id":"2305.15773","n_code_links":0,"syntology":null},{"paper":null,"title":"Convergence analysis and acceleration of the smoothing methods for solving extensive-form games","date":"2023-03-20","arxiv_id":"2303.11046","n_code_links":0,"syntology":null},{"paper":null,"title":"Understanding Emergent Behaviours in Multi-Agent Systems with Evolutionary Game Theory","date":"2022-05-15","arxiv_id":"2205.07369","n_code_links":0,"syntology":null},{"paper":null,"title":"Explainable Artificial Intelligence for Exhaust Gas Temperature of Turbofan Engines","date":"2022-03-24","arxiv_id":"2203.13108","n_code_links":0,"syntology":null},{"paper":"/paper/edge-augmented-graph-transformers-global-self","title":"Global Self-Attention as a Replacement for Graph Convolution","date":"2021-08-07","arxiv_id":"2108.03348","n_code_links":3,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":0}}],"papers_shown":10,"tasks":[{"task":"/task/edge-classification","name":"Edge Classification","papers":1},{"task":"/task/explainable-artificial-intelligence","name":"Explainable artificial intelligence","papers":1},{"task":"/task/form","name":"Form","papers":1},{"task":"/task/graph-classification","name":"Graph Classification","papers":1},{"task":"/task/graph-learning","name":"Graph Learning","papers":1},{"task":"/task/graph-property-prediction","name":"Graph Property Prediction","papers":1},{"task":"/task/graph-regression","name":"Graph Regression","papers":1},{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/kolmogorov-arnold-networks","name":"Kolmogorov-Arnold Networks","papers":1},{"task":"/task/link-prediction","name":"Link Prediction","papers":1},{"task":"/task/node-classification","name":"Node Classification","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":1},{"task":"/task/symbolic-regression","name":"Symbolic Regression","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/image-classification","name":"image-classification","papers":1},{"task":"/task/whole-slide-images","name":"whole slide images","papers":1}],"tasks_shown":18,"n_tasks":18,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":2},{"year":"2024","papers":2},{"year":"2025","papers":3}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/egt"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}