paper-with-me

홈 › Papers

GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs

2020-10-29 · Hao Xu, Shengqi Sang, Peizhen Bai, Laurence Yang, Haiping Lu

Heterogeneous graph representation learning aims to learn low-dimensional vector representations of different types of entities and relations to empower downstream tasks. Existing methods either capture semantic relationships but indirectly leverage node/edge attributes in a complex way, or leverage node/edge attributes directly without taking semantic relationships into account. When involving multiple convolution operations, they also have poor scalability. To overcome these limitations, this paper proposes a flexible and efficient Graph information propagation Network (GripNet) framework. Specifically, we introduce a new supergraph data structure consisting of supervertices and superedges. A supervertex is a semantically-coherent subgraph. A superedge defines an information propagation path between two supervertices. GripNet learns new representations for the supervertex of interest by propagating information along the defined path using multiple layers. We construct multiple large-scale graphs and evaluate GripNet against competing methods to show its superiority in link prediction, node classification, and data integration.

📄 PDF Abstract BibTeX arXiv:2010.15914

Code (1)

NYXFLOWER/GripNet 공식 구현 pytorch

Tasks

Data IntegrationGraph Representation LearningLink PredictionNode ClassificationRepresentation Learning

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Graph-Graph Similarity Network

2021-01-01 · Han Yue, Pengyu Hong, Hongfu Liu

Graph classification aims to predict the class label for an entire graph. Recently, Graph Neural Networks (GNNs)-based approaches become an essential strand to learn low-dimensional continuous embeddings of the entire gr…

ClassificationGeneral ClassificationGraph ClassificationGraph Similarity+1

Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks

2026-06-08 · Chentao Li, Han Guo arxiv

During the training of large Transformer models, attention masks regulate the scope and direction of information flow across a sequence. Numerous mask variants exist, and operators such as FlexAttention already support a…

GFlowNet Foundations

2021-11-17 · Yoshua Bengio, Salem Lahlou, Tristan Deleu, Edward J. Hu 외

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them approximately sample in proportion to a…

Active Learning

Tensor Graph Convolutional Networks for Text Classification

2020-01-12 · Xien Liu, Xinxin You, Xiao Zhang, Ji Wu 외

Compared to sequential learning models, graph-based neural networks exhibit some excellent properties, such as ability capturing global information. In this paper, we investigate graph-based neural networks for text clas…

ClassificationGeneral Classificationtext-classificationText Classification

DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation

2021-06-21 · Yifan Wang, Suyao Tang, Yuntong Lei, Weiping Song 외

Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems since it can model rich context information in user-item interactions. Graph neural network is a…

Collaborative FilteringGraph AttentionGraph Neural NetworkRecommendation Systems