A Capsule Network-based Model for Learning Node Embeddings
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}.
Code (1)
Tasks
General ClassificationNode ClassificationSimilar Papers 제목 키워드 기반
Capsule Graph Neural Network
The high-quality node embeddings learned from the Graph Neural Networks (GNNs) have been applied to a wide range of node-based applications and some of them have achieved state-of-the-art (SOTA) performance. However, whe…
Graph ClassificationGraph Neural NetworkHierarchical Graph Capsule Network
Graph Neural Networks (GNNs) draw their strength from explicitly modeling the topological information of structured data. However, existing GNNs suffer from limited capability in capturing the hierarchical graph represen…
Graph ClassificationNCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification
Message passing has evolved as an effective tool for designing Graph Neural Networks (GNNs). However, most existing methods for message passing simply sum or average all the neighboring features to update node representa…
ClassificationGraph Neural NetworkNode ClassificationSiamese Capsule Network for End-to-End Speaker Recognition In The Wild
We propose an end-to-end deep model for speaker verification in the wild. Our model uses thin-ResNet for extracting speaker embeddings from utterances and a Siamese capsule network and dynamic routing as the Back-end to …
Speaker RecognitionSpeaker VerificationPR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning
Capsule Networks (CapsNets) show exceptional graph representation capacity via dynamic routing and vectorized hierarchical representations, but they model the complex geometries of real\-world graphs poorly by fixed\-cur…
Graph Representation LearningGraph ClassificationGraph Learning