activity
20182023
most citedMultivariate Time Series Forecasting with Dynamic Graph Neural ODEs

182 citations · 431 across the 40 of their papers we have counts for

collaborators
Showing 2022 · cs.LGShow all

11 papers · 2 filters

cs.LG2022★ 3 cited

AutoPINN: When AutoML Meets Physics-Informed Neural Networks

Xinle Wu, Dalin Zhang, Miao Zhang +5

Physics-Informed Neural Networks (PINNs) have recently been proposed to solve scientific and engineering problems, where physical laws are introduced into neural networks as prior…

cs.LG2022★ 1 cited

Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting

Yunyao Cheng, Chenjuan Guo, Kaixuan Chen +6

Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT…

cs.LG2022★ 1 cited

Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

Xinle Wu, Dalin Zhang, Miao Zhang +3

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The ke…

cs.LG2022★ 4 cited

A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysis

Yan Zhao, Liwei Deng, Xuanhao Chen +7

The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energ…

cs.LG2022★ 2 cited

Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey

Dalin Zhang, Kaixuan Chen, Yan Zhao +3

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of tasks, and deep learning holds the potential to advance a multitude of applications, includ…

cs.LG2022

TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision

Alexander Bartler, Florian Bender, Felix Wiewel +1

Nowadays, deep neural networks outperform humans in many tasks. However, if the input distribution drifts away from the one used in training, their performance drops significantly.…