Search Results for author: Tijin Yan

Found 4 papers, 1 papers with code

ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models

1 code implementation18 Jun 2021 Tijin Yan, Hongwei Zhang, Tong Zhou, Yufeng Zhan, Yuanqing Xia

However, many existing works can not be widely used because of the constraints of functional form of generative models or the sensitivity to hyperparameters.

Probabilistic Time Series Forecasting Time Series +1

Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective

no code implementations24 Sep 2020 Hongwei Zhang, Tijin Yan, Zenjun Xie, Yuanqing Xia, Yuan Zhang

Based on our theoretical and empirical analysis, we establish a universal theoretical framework of GCN from an optimization perspective and derive a novel convolutional kernel named GCN+ which has lower parameter amount while relieving the over-smoothing inherently.

General Classification Node Classification

Stochastic Graph Recurrent Neural Network

no code implementations1 Sep 2020 Tijin Yan, Hongwei Zhang, Zirui Li, Yuanqing Xia

In addition, to alleviate KL-vanishing problem in SGRNN, a simple and interpretable structure is proposed based on the lower bound of KL-divergence.

Representation Learning Variational Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.