Loading...
Yan Lin's Page

Hi, my name is Yan Lin,
A CS Researcher

My research interest include Spatial-temporal Data Mining, Trajectory Mining, Representation Learning, and Pre-training.

I received the B.S. degree in computer science from Beijing Jiaotong University in 2019, and the Ph.D. degree in computer science in 2024.
I am currently a Post-Doc. in the DAISY group, Aalborg University.

News

April 2024

STGED accepted by TKDE'24

Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery

April 2024

A Talk in SpatialDI'24

Tutorial: Self-supervised learning of spatio-temporal trajectories

March 2024

Ph.D. Thesis Defense

Title: Self-supervised Learning of Spatial-temporal Trajectory Data

January 2024

MMTEC accepted by TKDE'24

Pre-training General Trajectory Embeddings with Maximum Multi-view Entropy Coding

May 2023

DOT accepted by SIGMOD'24

Origin-Destination Travel Time Oracle for Map-based Services

Latest Publications

IEEE TKDE 2024

Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder for Map-Constrained Trajectory Recovery

Recovering intermediate missing GPS points in a sparse trajectory with the proposed Micro-Macro Spatial-Temporal Graph-based Encoder-Decoder (MM-STGED).

Spatio-temporal Trajectory Recovery

IEEE TKDE 2024

Pre-training General Trajectory Embeddings with Maximum Multi-view Entropy Coding

Learning general and comprehensive trajectory embeddings that are useful for a wide variety of downstream tasks with the proposed propose Maximum Multi-view Trajectory Entropy Coding (MMTEC).

Spatio-temporal Trajectory Learning Representation

ACM SIGMOD 2024

Origin-Destination Travel Time Oracle for Map-based Services

Solving the Origin-Destination (OD) travel time oracle (ODT-Oracle) problem with a two-stage framework called Diffusion-based Origin-destination Travel Time Estimation (DOT).

Spatio-temporal Diffusion Model ETA

KBS 2023

Inductive and Adaptive Graph Convolution Networks Equipped with Constraint Task for Spatial-Temporal Traffic Data Kriging

Proposing an Inductive and Adaptive Graph Convolution Networks (IAGCN) for spatio-temporal traffic data kriging in an inductive manner.

Spatio-temporal ST Graph

NeurIPS 2023

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

Effectively capture both long- and short-term repetitive patterns in time series with the proposed Water-wave Information Transmission and Recurrent Acceleration Network (WITRAN).

Time Series

AAAI 2023

Contrastive Pre-training with Adversarial Perturbations for Check-In Sequence Representation Learning

Representation learning of check-in sequences with the proposed contrastive pre-training model with adversarial perturbations for check-in sequence representation learning (CACSR).

Spatio-temporal Check-in

Recent Projects

Image
Image

Prompt Genius

All-purpose prompts with hierarchical classification system and multi-language support.

Learn More

Overleaf Copilot

Powered by Large Language Models, OverleafCopilot is a plugin designed to elevate the academic writing experience on Overleaf.

Learn More