paper-with-me

Papers

Rethinking Graph Transformer Architecture Design for Node Classification

2024-10-15 · Jiajun Zhou, Xuanze Chen, Chenxuan Xie, Yu Shanqing, Qi Xuan, Xiaoniu Yang

Graph Transformer (GT), as a special type of Graph Neural Networks (GNNs), utilizes multi-head attention to facilitate high-order message passing. However, this also imposes several limitations in node classification applications: 1) nodes are susceptible to global noise; 2) self-attention computation cannot scale well to large graphs. In this work, we conduct extensive observational experiments to explore the adaptability of the GT architecture in node classification tasks and draw several conclusions: the current multi-head self-attention module in GT can be completely replaceable, while the feed-forward neural network module proves to be valuable. Based on this, we decouple the propagation (P) and transformation (T) of GNNs and explore a powerful GT architecture, named GNNFormer, which is based on the P/T combination message passing and adapted for node classification in both homophilous and heterophilous scenarios. Extensive experiments on 12 benchmark datasets demonstrate that our proposed GT architecture can effectively adapt to node classification tasks without being affected by global noise and computational efficiency limitations.

📄 PDF Abstract BibTeX arXiv:2410.11189

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationComputational EfficiencyNode Classification

Methods 이 논문이 사용한 방법론

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…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
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 $x$…

Similar Papers 제목 키워드 기반

NN-Former: Rethinking Graph Structure in Neural Architecture Representation

2025-07-01 · Ruihan Xu, Haokui Zhang, Yaowei Wang, Wei Zeng 외 arxiv

The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and tra…

NN-Former: Rethinking Graph Structure in Neural Architecture Representation

2025-01-01 · CVPR 2025 1 · Ruihan Xu, Haokui Zhang, YaoWei Wang, Wei Zeng 외

The growing use of deep learning necessitates efficient network design and deployment, making neural predictors vital for estimating attributes such as accuracy and latency. Recently, Graph Neural Networks (GNNs) and…

Rethinking Graph Transformers with Spectral Attention

2021-06-07 · NeurIPS 2021 12 · Devin Kreuzer, Dominique Beaini, William L. Hamilton, Vincent Létourneau 외

In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly …

Rethinking Tokenized Graph Transformers for Node Classification

2025-02-12 · Jinsong Chen, Chenyang Li, Gaichao Li, John E. Hopcroft 외

Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token s…

ClassificationNode ClassificationRepresentation Learning

Graph Propagation Transformer for Graph Representation Learning

2023-05-19 · Zhe Chen, Hao Tan, Tao Wang, Tianrun Shen 외

This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the a…

Graph LearningGraph Property PredictionGraph RegressionGraph Representation Learning+2