Learning Graph Representations with Embedding Propagation

2017-10-09 · NeurIPS 2017 12 · Alberto Garcia-Duran, Mathias Niepert

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.

📄 PDF Abstract BibTeX arXiv:1710.03059

Code (0)

등록된 구현이 없습니다.

Embedding Propagation: Smoother Manifold for Few-Shot Classification

2020-03-09 · ECCV 2020 8 · Pau Rodríguez, Issam Laradji, Alexandre Drouin, Alexandre Lacoste

Few-shot classification is challenging because the data distribution of the training set can be widely different to the test set as their classes are disjoint. This distribution shift often results in poor generalization…

Classification Few-Shot Image Classification General Classification Transductive Learning

Quaternion-Based Graph Convolution Network for Recommendation

2021-11-20 · Yaxing Fang, Pengpeng Zhao, Guanfeng Liu, Yanchi Liu 외

Graph Convolution Network (GCN) has been widely applied in recommender systems for its representation learning capability on user and item embeddings. However, GCN is vulnerable to noisy and incomplete graphs, which are …

Recommendation Systems Representation Learning

Course Concept Extraction in MOOCs via Embedding-Based Graph Propagation

2017-11-01 · IJCNLP 2017 11 · Liangming Pan, Xiaochen Wang, Chengjiang Li, Juanzi Li 외

Massive Open Online Courses (MOOCs), offering a new way to study online, are revolutionizing education. One challenging issue in MOOCs is how to design effective and fine-grained course concepts such that students with d…

DyGCN: Dynamic Graph Embedding with Graph Convolutional Network

2021-04-07 · Zeyu Cui, Zekun Li, Shu Wu, XiaoYu Zhang 외

Graph embedding, aiming to learn low-dimensional representations (aka. embeddings) of nodes, has received significant attention recently. Recent years have witnessed a surge of efforts made on static graphs, among which …

Dynamic graph embedding Graph Embedding

Domain-adaptive Message Passing Graph Neural Network

2023-08-31 · Xiao Shen, Shirui Pan, Kup-Sze Choi, Xi Zhou

Cross-network node classification (CNNC), which aims to classify nodes in a label-deficient target network by transferring the knowledge from a source network with abundant labels, draws increasing attention recently. To…

Domain Adaptation GRAPH DOMAIN ADAPTATION Graph Neural Network Node Classification