TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Node Classification	Cora	Caps2NE	Accuracy	80.53%	# 65
Node Classification	Pubmed	Caps2NE	Accuracy	78.45%	# 54

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/a-capsule-network-based-model-for-learning/node-classification-on-pubmed)](https://paperswithcode.com/sota/node-classification-on-pubmed?p=a-capsule-network-based-model-for-learning)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/a-capsule-network-based-model-for-learning/node-classification-on-cora)](https://paperswithcode.com/sota/node-classification-on-cora?p=a-capsule-network-based-model-for-learning)`

A Capsule Network-based Model for Learning Node Embeddings

12 Nov 2019 · Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung ·

In this paper, we focus on learning low-dimensional embeddings for nodes in graph-structured data. To achieve this, we propose Caps2NE -- a new unsupervised embedding model leveraging a network of two capsule layers. Caps2NE induces a routing process to aggregate feature vectors of context neighbors of a given target node at the first capsule layer, then feed these features into the second capsule layer to infer a plausible embedding for the target node. Experimental results show that our proposed Caps2NE obtains state-of-the-art performances on benchmark datasets for the node classification task. Our code is available at: \url{https://github.com/daiquocnguyen/Caps2NE}.

PDF Abstract