paper-with-me

Papers

Variational Graph Normalized Auto-Encoders

2021-08-18 · Seong Jin Ahn, Myoung Ho Kim

Link prediction is one of the key problems for graph-structured data. With the advancement of graph neural networks, graph autoencoders (GAEs) and variational graph autoencoders (VGAEs) have been proposed to learn graph embeddings in an unsupervised way. It has been shown that these methods are effective for link prediction tasks. However, they do not work well in link predictions when a node whose degree is zero (i.g., isolated node) is involved. We have found that GAEs/VGAEs make embeddings of isolated nodes close to zero regardless of their content features. In this paper, we propose a novel Variational Graph Normalized AutoEncoder (VGNAE) that utilize L2-normalization to derive better embeddings for isolated nodes. We show that our VGNAEs outperform the existing state-of-the-art models for link prediction tasks. The code is available at https://github.com/SeongJinAhn/VGNAE.

📄 PDF Abstract BibTeX arXiv:2108.08046

Code (1)

SeongJinAhn/VGNAE 공식 구현 pytorch

Tasks

Link PredictionPrediction

Similar Papers 제목 키워드 기반

Inducing Interpretable Representations with Variational Autoencoders

2016-11-22 · N. Siddharth, Brooks Paige, Alban Desmaison, Jan-Willem van de Meent 외

We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representations through approximate variational infere…

General ClassificationVariational Inference

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

2020-02-18 · pproximateinference AABI Symposium 2019 12 · Ziyu Wang, Shuyu Cheng, Yueru Li, Jun Zhu 외

Score matching provides an effective approach to learning flexible unnormalized models, but its scalability is limited by the need to evaluate a second-order derivative. In this paper, we present a scalable approximation…

Semi-Implicit Graph Variational Auto-Encoders

2019-08-19 · NeurIPS 2019 12 · Arman Hasanzadeh, Ehsan Hajiramezanali, Nick Duffield, Krishna R. Narayanan 외

Semi-implicit graph variational auto-encoder (SIG-VAE) is proposed to expand the flexibility of variational graph auto-encoders (VGAE) to model graph data. SIG-VAE employs a hierarchical variational framework to enable n…

DecoderVariational Inference

ResVGAE: Going Deeper with Residual Modules for Link Prediction

2021-05-03 · Indrit Nallbani, Reyhan Kevser Keser, Aydin Ayanzadeh, Nurullah Çalık 외

Graph autoencoders are efficient at embedding graph-based data sets. Most graph autoencoder architectures have shallow depths which limits their ability to capture meaningful relations between nodes separated by multi-ho…

Link PredictionPredictionRepresentation Learning

Dynamic Joint Variational Graph Autoencoders

2019-10-04 · Sedigheh Mahdavi, Shima Khoshraftar, Aijun An

Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dyna…

ClusteringGraph ClusteringGraph EmbeddingLearning Network Representations+2