paper-with-me

Papers

Optimizing Graph Transformer Networks with Graph-based Techniques

2021-06-16 · Loc Hoang, Udit Agarwal, Gurbinder Gill, Roshan Dathathri, Abhik Seal, Brian Martin, Keshav Pingali

Graph transformer networks (GTN) are a variant of graph convolutional networks (GCN) that are targeted to heterogeneous graphs in which nodes and edges have associated type information that can be exploited to improve inference accuracy. GTNs learn important metapaths in the graph, create weighted edges for these metapaths, and use the resulting graph in a GCN. Currently, the only available implementation of GTNs uses dense matrix multiplication to find metapaths. Unfortunately, the space overhead of this approach can be large, so in practice it is used only for small graphs. In addition, the matrix-based implementation is not fine-grained enough to use random-walk based methods to optimize metapath finding. In this paper, we present a graph-based formulation and implementation of the GTN metapath finding problem. This graph-based formulation has two advantages over the matrix-based approach. First, it is more space efficient than the original GTN implementation and more compute-efficient for metapath sizes of practical interest. Second, it permits us to implement a sampling method that reduces the number of metapaths that must be enumerated, allowing the implementation to be used for larger graphs and larger metapath sizes. Experimental results show that our implementation is $6.5\times$ faster than the original GTN implementation on average for a metapath length of 4, and our sampling implementation is $155\times$ faster on average than this implementation without compromising on the accuracy of the GTN.

📄 PDF Abstract BibTeX arXiv:2106.08500

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Graph Convolutional Networks 설명 없음
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability

2021-11-19 · Weilin Cong, Yanhong Wu, Yuandong Tian, Mengting Gu 외

Transformers have achieved great success in several domains, including Natural Language Processing and Computer Vision. However, its application to real-world graphs is less explored, mainly due to its high computation c…

Graph LearningGraph Representation LearningRepresentation Learning

Graph Integrated Transformers for Community Detection in Social Networks

2026-01-07 · Heba Zahran, M. Omair Shafiq arxiv

Community detection is crucial for applications like targeted marketing and recommendation systems. Traditional methods rely on network structure, and embedding-based models integrate semantic information. However, there…

Recommendation SystemsCommunity Detection

SpecTRA: Spectral Transformer for Graph Representation Learning

2021-09-29 · Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Hiroki Kanezashi 외

Transformers have recently been applied in the more generic domain of graphs. For the same, researchers proposed various positional and structural encoding schemes to overcome the limitation of transformers in modeling t…

Graph Representation LearningRepresentation Learning

Invariant Graph Transformer for Out-of-Distribution Generalization

2025-08-01 · Tianyin Liao, Ziwei Zhang, Yufei Sun, Chunyu Hu 외 arxiv

Graph Transformers (GTs) have demonstrated great effectiveness across various graph analytical tasks. However, the existing GTs focus on training and testing graph data originated from the same distribution, but fail to …

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…