Semi-Implicit Neural Ordinary Differential Equations

Hong Zhang, Ying Liu, Romit Maulik

Research output: Contribution to journalConference articlepeer-review

Abstract

Classical neural ODEs trained with explicit methods are intrinsically limited by stability, crippling their efficiency and robustness for stiff learning problems that are common in graph learning and scientific machine learning. We present a semi-implicit neural ODE approach that exploits the partitionable structure of the underlying dynamics. Our technique leads to an implicit neural network with significant computational advantages over existing approaches because of enhanced stability and efficient linear solves during time integration. We show that our approach outperforms existing approaches on a variety of applications including graph classification and learning complex dynamical systems. We also demonstrate that our approach can train challenging neural ODEs where both explicit methods and fully implicit methods are intractable.

Original languageEnglish (US)
Pages (from-to)22416-22424
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume39
Issue number21
DOIs
StatePublished - Apr 11 2025
Event39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025 - Philadelphia, United States
Duration: Feb 25 2025Mar 4 2025

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Semi-Implicit Neural Ordinary Differential Equations'. Together they form a unique fingerprint.

Cite this