paper-with-me

Papers

Graph Attention Networks with Positional Embeddings

2021-05-09 · Liheng Ma, Reihaneh Rabbany, Adriana Romero-Soriano

Graph Neural Networks (GNNs) are deep learning methods which provide the current state of the art performance in node classification tasks. GNNs often assume homophily -- neighboring nodes having similar features and labels--, and therefore may not be at their full potential when dealing with non-homophilic graphs. In this work, we focus on addressing this limitation and enable Graph Attention Networks (GAT), a commonly used variant of GNNs, to explore the structural information within each graph locality. Inspired by the positional encoding in the Transformers, we propose a framework, termed Graph Attentional Networks with Positional Embeddings (GAT-POS), to enhance GATs with positional embeddings which capture structural and positional information of the nodes in the graph. In this framework, the positional embeddings are learned by a model predictive of the graph context, plugged into an enhanced GAT architecture, which is able to leverage both the positional and content information of each node. The model is trained jointly to optimize for the task of node classification as well as the task of predicting graph context. Experimental results show that GAT-POS reaches remarkable improvement compared to strong GNN baselines and recent structural embedding enhanced GNNs on non-homophilic graphs.

📄 PDF Abstract BibTeX arXiv:2105.04037

Code (0)

등록된 구현이 없습니다.

Tasks

Graph AttentionNode ClassificationPOS

Methods 이 논문이 사용한 방법론

GAT A Graph Attention Network (GAT) is a neural network architecture that operates on graph-structured data, leveraging masked self-attentional layers to address the shortcomings…

Similar Papers 제목 키워드 기반

Dual Triangle Attention: Effective Bidirectional Attention Without Positional Embeddings

2026-04-09 · Logan Hallee, Jason P. Gleghorn arxiv

Bidirectional transformers are the foundation of many sequence modeling tasks across natural, biological, and chemical language domains, but they are permutation-invariant without explicit positional embeddings. In contr…

Do traveling waves make good positional encodings?

2025-11-11 · Chase van de Geijn, Ayush Paliwal, Timo Lüddecke, Alexander S. Ecker arxiv

Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent…

Graph Attention for Heterogeneous Graphs with Positional Encoding

2025-04-03 · Nikhil Shivakumar Nayak

Graph Neural Networks (GNNs) have emerged as the de facto standard for modeling graph data, with attention mechanisms and transformers significantly enhancing their performance on graph-based tasks. Despite these advance…

Graph AttentionLink PredictionNode Classification

Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings

2023-05-23 · Ta-Chung Chi, Ting-Han Fan, Li-Wei Chen, Alexander I. Rudnicky 외

The use of positional embeddings in transformer language models is widely accepted. However, recent research has called into question the necessity of such embeddings. We further extend this inquiry by demonstrating that…

Language ModelingLanguage Modelling

Position Information Emerges in Causal Transformers Without Positional Encodings via Similarity of Nearby Embeddings

2024-12-30 · Chunsheng Zuo, Pavel Guerzhoy, Michael Guerzhoy

Transformers with causal attention can solve tasks that require positional information without using positional encodings. In this work, we propose and investigate a new hypothesis about how positional information can be…

Position