paper-with-me

홈 › Papers

Transformer for Graphs: An Overview from Architecture Perspective

2022-02-17 · Erxue Min, Runfa Chen, Yatao Bian, Tingyang Xu, Kangfei Zhao, Wenbing Huang, Peilin Zhao, Junzhou Huang, Sophia Ananiadou, Yu Rong

Recently, Transformer model, which has achieved great success in many artificial intelligence fields, has demonstrated its great potential in modeling graph-structured data. Till now, a great variety of Transformers has been proposed to adapt to the graph-structured data. However, a comprehensive literature review and systematical evaluation of these Transformer variants for graphs are still unavailable. It's imperative to sort out the existing Transformer models for graphs and systematically investigate their effectiveness on various graph tasks. In this survey, we provide a comprehensive review of various Graph Transformer models from the architectural design perspective. We first disassemble the existing models and conclude three typical ways to incorporate the graph information into the vanilla Transformer: 1) GNNs as Auxiliary Modules, 2) Improved Positional Embedding from Graphs, and 3) Improved Attention Matrix from Graphs. Furthermore, we implement the representative components in three groups and conduct a comprehensive comparison on various kinds of famous graph data benchmarks to investigate the real performance gain of each component. Our experiments confirm the benefits of current graph-specific modules on Transformer and reveal their advantages on different kinds of graph tasks.

📄 PDF Abstract BibTeX arXiv:2202.08455

Code (1)

qwerfdsaplking/graph-trans 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LapEigen 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Attending to Graph Transformers

2023-02-08 · Luis Müller, Mikhail Galkin, Christopher Morris, Ladislav Rampášek

Recently, transformer architectures for graphs emerged as an alternative to established techniques for machine learning with graphs, such as (message-passing) graph neural networks. So far, they have shown promising empi…

A Survey on Structure-Preserving Graph Transformers

2024-01-29 · Van Thuy Hoang, O-Joun Lee

The transformer architecture has shown remarkable success in various domains, such as natural language processing and computer vision. When it comes to graph learning, transformers are required not only to capture the in…

Graph LearningSurvey

The Power of the Weisfeiler-Leman Algorithm for Machine Learning with Graphs

2021-05-12 · Christopher Morris, Matthias Fey, Nils M. Kriege

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for (supervised) machine learning with gr…

BIG-bench Machine LearningNode Classification

What does Transformer learn about source code?

2022-07-18 · Kechi Zhang, Ge Li, Zhi Jin

In the field of source code processing, the transformer-based representation models have shown great powerfulness and have achieved state-of-the-art (SOTA) performance in many tasks. Although the transformer models proce…

Variable misuse

Logistics, Graphs, and Transformers: Towards improving Travel Time Estimation

2022-07-12 · Natalia Semenova, Vadim Porvatov, Vladislav Tishin, Artyom Sosedka 외

The problem of travel time estimation is widely considered as the fundamental challenge of modern logistics. The complex nature of interconnections between spatial aspects of roads and temporal dynamics of ground transpo…

regressionTravel Time Estimation