paper-with-me

홈 › Papers

GRPE: Relative Positional Encoding for Graph Transformer

2022-01-30 · Wonpyo Park, WoongGi Chang, Donggeon Lee, Juntae Kim, Seung-won Hwang

We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using bias terms. The former loses preciseness of relative position from linearization, while the latter loses a tight integration of node-edge and node-topology interaction. To overcome the weakness of the previous approaches, our method encodes a graph without linearization and considers both node-topology and node-edge interaction. We name our method Graph Relative Positional Encoding dedicated to graph representation learning. Experiments conducted on various graph datasets show that the proposed method outperforms previous approaches significantly. Our code is publicly available at https://github.com/lenscloth/GRPE.

📄 PDF Abstract BibTeX arXiv:2201.12787

Code (1)

lenscloth/grpe 공식 구현 pytorch

Tasks

Graph ClassificationGraph RegressionGraph Representation LearningMolecular Property PredictionPositionRepresentation Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 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…
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…
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…

Similar Papers 제목 키워드 기반

SLGTformer: An Attention-Based Approach to Sign Language Recognition

2022-12-21 · Neil Song, Yu Xiang

Sign language is the preferred method of communication of deaf or mute people, but similar to any language, it is difficult to learn and represents a significant barrier for those who are hard of hearing or unable to spe…

Sign Language Recognition

Comparing Graph Transformers via Positional Encodings

2024-02-22 · Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri 외

The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of position…

Navigate

Linearized Relative Positional Encoding

2023-07-18 · Zhen Qin, Weixuan Sun, Kaiyue Lu, Hui Deng 외

Relative positional encoding is widely used in vanilla and linear transformers to represent positional information. However, existing encoding methods of a vanilla transformer are not always directly applicable to a line…

image-classificationImage ClassificationLanguage ModelingLanguage Modelling+2

A standard transformer and attention with linear biases for molecular conformer generation

2025-06-24 · Viatcheslav Gurev, Timothy Rumbell

Sampling low-energy molecular conformations, spatial arrangements of atoms in a molecule, is a critical task for many different calculations performed in the drug discovery and optimization process. Numerous specialized …

Drug Discovery

Graph Transformers without Positional Encodings

2024-01-31 · Ayush Garg

Recently, Transformers for graph representation learning have become increasingly popular, achieving state-of-the-art performance on a wide-variety of graph datasets, either alone or in combination with message-passing g…

Graph ClassificationGraph RegressionGraph Representation LearningNode Classification+1