AIConfPaper
← Search

Lars Schmidt-Thieme

10 accepted papers

2026

Reliable Probabilistic Forecasting of Irregular Time Series through Marginalization-Consistent Flows

Vijaya Krishna Yalavarthi, Randolf Scholz, Christian Klötergens, Kiran Madhusudhanan, Stefan Born, Lars Schmidt-Thieme
ICLR 2026poster

Probabilistic forecasting of joint distributions for irregular time series with missing values is an underexplored area in machine learning. Existing models, such as Gaussian Process Regression and ProFITi, are limited: while ProFITi is highly expressive due to its use of normalizing flows, it often…

Cited by 0Source ↗Scholar ↗
2026

Rethinking Convolutional Networks for Attribute-Aware Sequential Recommendation

Shereen Elsayed, Ngoc Son Le, Ahmed Rashed, Lars Schmidt-Thieme
IJCAI 2026

Attribute-aware sequential recommendation entails predicting the next item a user will interact with based on a chronologically ordered history of past interactions, enriched with item attributes. Existing methods typically leverage self-attention mechanisms to aggregate the entire sequence into a u

Cited by 0Scholar ↗
2025

Motif-aware Graph Neural Networks for Networked Time Series Imputation

Nourhan Ahmed, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme
AAAI 2025technical

Networked time series are time series on a graph, one for each node, with applications in traffic and weather monitoring. Graph neural networks are natural candidates for networked time series imputation and have recently outperformed existing alternatives such as recurrent and generative models for…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time-Series Forecasting Based on Biological ODEs

Christian Klötergens, Vijaya Krishna Yalavarthi, Randolf Scholz, Maximilian Stubbemann, Stefan Born, Lars Schmidt-Thieme
ICLR 2025poster

State-of-the-art methods for forecasting irregularly sampled time series with missing values predominantly rely on just four datasets and a few small toy examples for evaluation. While ordinary differential equations (ODE) are the prevalent models in science and engineering, a baseline model that fo…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Probabilistic Forecasting of Irregularly Sampled Time Series with Missing Values via Conditional Normalizing Flows

Vijaya Krishna Yalavarthi, Randolf Scholz, Stefan Born, Lars Schmidt-Thieme
AAAI 2025technical

Probabilistic forecasting of irregularly sampled multivariate time series with missing values is crucial for decision-making in various domains, including health care, astronomy, and climate. State-of-the-art methods estimate only marginal distributions of observations in single channels and at sing…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Robust Hyperbolic Learning with Curvature-Aware Optimization

Ahmad Bdeir, Johannes Burchert, Lars Schmidt-Thieme, Niels Landwehr
NeurIPS 2025poster

Hyperbolic deep learning has become a growing research direction in computer vision due to the unique properties afforded by the alternate embedding space. The negative curvature and exponentially growing distance metric provide a natural framework for capturing hierarchical relationships between da…

Cited by 4Source ↗Scholar ↗
2024

A Cross-Domain Benchmark for Active Learning

Thorben Werner, Johannes Burchert, Maximilian Stubbemann, Lars Schmidt-Thieme
NeurIPS 2024poster

Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fact that lifts from literature generalize poorly and that only a small number of repetitions of experiments are conducted…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

GraFITi: Graphs for Forecasting Irregularly Sampled Time Series

Vijaya Krishna Yalavarthi, Kiran Madhusudhanan, Randolf Scholz, Nourhan Ahmed, Johannes Burchert, Shayan Jawed +2
AAAI 2024technical

Forecasting irregularly sampled time series with missing values is a crucial task for numerous real-world applications such as healthcare, astronomy, and climate sciences. State-of-the-art approaches to this problem rely on Ordinary Differential Equations (ODEs) which are known to be slow and often…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Zero-shot AutoML with Pretrained Models

Ekrem Öztürk, Fabio Ferreira, Hadi Jomaa, Lars Schmidt-Thieme, Josif Grabocka, Frank Hutter
ICML 2022spotlight

Given a new dataset D and a low compute budget, how should we choose a pre-trained model to fine-tune to D, and set the fine-tuning hyperparameters without risking overfitting, particularly if D is small? Here, we extend automated machine learning (AutoML) to best make these choices. Our domain-inde…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗