Category: GCN

GCN, GNN, OOV, Word Embeddings

Paper Reading: Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks

venue: ACL 2019 The paper proposes a GCN-based method to produce word embeddings for out-of-vocabulary(OOV) words. 1. Graph Construction To construct a knowledge graph, vocabulary is constructed from Wikipedia English dataset (3B tokens). To note that, this vocabulary includes OOV words which are not in the vocabulary of pre-trained embeddings such as GLOVE. For each node/word, they define the concatenation of Wikipedia page summary and … Continue reading Paper Reading: Out-of-Vocabulary Embedding Imputation with Grounded Language Information by Graph Convolutional Networks

Zhiyu ChenLeave a comment
GCN, Paper Reading, Text Classification

Paper Reading: Tensor Graph Convolutional Networks for Text Classification

The basic notations for GCN are the same with this post. 1. Graph Tensor Definition Here we first describe the formal definition of graph tensor which consists of a series of graphs. is a graph tensor, where and , if and (when ). Where is the i-th graph in the graph tensor, is the set of i-th graph nodes, is the set of the i-th … Continue reading Paper Reading: Tensor Graph Convolutional Networks for Text Classification

Zhiyu ChenLeave a comment
GCN, Paper Reading

Paper Reading: Modeling Relational Data with Graph Convolutional Networks

This paper introduce Relational Graph Convolutional Networks (R-GCNs) which deal with relational data. In addition, techniques for parameter sharing and to enforce sparsity constraints are introduced to apply R-GCNs to multigraphs with large numbers of relations. 1. Relational Graph Convolutional Networks Given directed and labeled multi-graphs as with nodes and labeled edges , where is a relation type. In a relational multi-graph, R-GCNs calculates the … Continue reading Paper Reading: Modeling Relational Data with Graph Convolutional Networks

Zhiyu ChenLeave a comment