J
Jian Li
Researcher at Tsinghua University
Publications - 206
Citations - 6148
Jian Li is an academic researcher from Tsinghua University. The author has contributed to research in topics: Approximation algorithm & Time complexity. The author has an hindex of 35, co-authored 197 publications receiving 4632 citations. Previous affiliations of Jian Li include Fudan University & University of Maryland, College Park.
Papers
More filters
Proceedings ArticleDOI
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec.
TL;DR: The NetMF method offers significant improvements over DeepWalk and LINE for conventional network mining tasks and provides the theoretical connections between skip-gram based network embedding algorithms and the theory of graph Laplacian.
Proceedings ArticleDOI
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
TL;DR: In this paper, a unified matrix factorization framework for skip-gram based network embedding was proposed, leading to a better understanding of latent network representation learning and the theory of graph Laplacian.
Proceedings Article
BRITS: Bidirectional Recurrent Imputation for Time Series
TL;DR: BRITS is a novel method based on recurrent neural networks for missing value imputation in time series data that directly learns the missing values in a bidirectional recurrent dynamical system, without any specific assumption.
Proceedings Article
When Will You Arrive? Estimating Travel Time Based on Deep Neural Networks
TL;DR: An end-to-end Deep learning framework for Travel Time Estimation (called DeepTTE) that estimates the travel time of the whole path directly, and presents a geo-convolution operation by integrating the geographic information into the classical convolution, capable of capturing spatial correlations.
Proceedings ArticleDOI
DeepSD: Supply-Demand Prediction for Online Car-Hailing Services Using Deep Neural Networks
TL;DR: This paper presents an end-to-end framework called Deep Supply-Demand (DeepSD) using a novel deep neural network structure that can automatically discover complicated supply-demand patterns from the car-hailing service data while only requires a minimal amount hand-crafted features.