paper-with-me

Papers

Topology-Informed Graph Transformer

2024-02-03 · Yun Young Choi, Sun Woo Park, Minho Lee, Youngho Woo

Transformers have revolutionized performance in Natural Language Processing and Vision, paving the way for their integration with Graph Neural Networks (GNNs). One key challenge in enhancing graph transformers is strengthening the discriminative power of distinguishing isomorphisms of graphs, which plays a crucial role in boosting their predictive performances. To address this challenge, we introduce 'Topology-Informed Graph Transformer (TIGT)', a novel transformer enhancing both discriminative power in detecting graph isomorphisms and the overall performance of Graph Transformers. TIGT consists of four components: A topological positional embedding layer using non-isomorphic universal covers based on cyclic subgraphs of graphs to ensure unique graph representation: A dual-path message-passing layer to explicitly encode topological characteristics throughout the encoder layers: A global attention mechanism: And a graph information layer to recalibrate channel-wise graph features for better feature representation. TIGT outperforms previous Graph Transformers in classifying synthetic dataset aimed at distinguishing isomorphism classes of graphs. Additionally, mathematical analysis and empirical evaluations highlight our model's competitive edge over state-of-the-art Graph Transformers across various benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2402.02005

Code (2)

leemingo/tigt 공식 구현 pytorch
leemingo/cy2mixer pytorch

Tasks

Graph ClassificationGraph RegressionInductive BiasNode Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
LapEigen 설명 없음
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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

Spatial Shortcuts in Graph Neural Controlled Differential Equations

2024-10-25 · Michael Detzel, Gabriel Nobis, Jackie Ma, Wojciech Samek

We incorporate prior graph topology information into a Neural Controlled Differential Equation (NCDE) to predict the future states of a dynamical system defined on a graph. The informed NCDE infers the future dynamics at…

Position

Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning

2025-11-26 · Kaifeng Hong, Yinglong Zhang, Xiaoying Hong, Xuewen Xia 외 arxiv

Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusi…

Representation Learning

Joint Sensor Deployment and Physics-Informed Graph Transformer for Smart Grid Attack Detection

2026-02-16 · Mariam Elnour, Mohammad AlShaikh Saleh, Rachad Atat, Xiang Huo 외 arxiv

This paper proposes a joint multi-objective optimization framework for strategic sensor placement in power systems to enhance attack detection. A novel physics-informed graph transformer network (PIGTN)-based detection m…

HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning

2025-04-03 · Hao Wang, Shuo Zhang, Biao Leng

The computer vision community has witnessed an extensive exploration of vision transformers in the past two years. Drawing inspiration from traditional schemes, numerous works focus on introducing vision-specific inducti…

Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity

2026-08-01 · Yinlin Zhu, Di Wu, Yi Zhang, Xunkai Li 외 arxiv

Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopted across diverse domains. Federated mult…

Contrastive LearningGraph Learning