Search Results for author: Stephan Günnemann

Found 82 papers, 43 papers with code

Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning

no code implementations3 Jun 2022 Bertrand Charpentier, Ransalu Senanayake, Mykel Kochenderfer, Stephan Günnemann

Characterizing aleatoric and epistemic uncertainty can be used to speed up learning in a training environment, improve generalization to similar testing environments, and flag unfamiliar behavior in anomalous testing environments.

reinforcement-learning

Sampling-free Inference for Ab-Initio Potential Energy Surface Networks

no code implementations30 May 2022 Nicholas Gao, Stephan Günnemann

In recent work, the potential energy surface network (PESNet) has been proposed to reduce training time by solving the Schr\"odinger equation for many geometries simultaneously.

Numerical Integration

Predicting single-cell perturbation responses for unseen drugs

1 code implementation28 Apr 2022 Leon Hetzel, Simon Böhm, Niki Kilbertus, Stephan Günnemann, Mohammad Lotfollahi, Fabian Theis

Single-cell transcriptomics enabled the study of cellular heterogeneity in response to perturbations at the resolution of individual cells.

Drug Discovery Transfer Learning

How Do Graph Networks Generalize to Large and Diverse Molecular Systems?

no code implementations6 Apr 2022 Johannes Gasteiger, Muhammed Shuaibi, Anuroop Sriram, Stephan Günnemann, Zachary Ulissi, C. Lawrence Zitnick, Abhishek Das

Based on this analysis, we identify a smaller dataset that correlates well with the full OC20 dataset, and propose the GemNet-OC model, which outperforms the previous state-of-the-art on OC20 by 16%, while reducing training time by a factor of 10.

Initial Structure to Relaxed Energy (IS2RE)

Differentiable DAG Sampling

no code implementations ICLR 2022 Bertrand Charpentier, Simon Kibler, Stephan Günnemann

To this end, DP-DAG samples a DAG by successively (1) sampling a linear ordering of the node and (2) sampling edges consistent with the sampled linear ordering.

Variational Inference

Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space

no code implementations16 Mar 2022 Poulami Sinhamahapatra, Rajat Koner, Karsten Roscher, Stephan Günnemann

It is essential for safety-critical applications of deep neural networks to determine when new inputs are significantly different from the training distribution.

Contrastive Learning OOD Detection +1

Enabling Automated Machine Learning for Model-Driven AI Engineering

no code implementations6 Mar 2022 Armin Moin, Ukrit Wattanavaekin, Alexandra Lungu, Moharram Challenger, Atta Badii, Stephan Günnemann

Developing smart software services requires both Software Engineering and Artificial Intelligence (AI) skills.

Graph Data Augmentation for Graph Machine Learning: A Survey

1 code implementation17 Feb 2022 Tong Zhao, Gang Liu, Stephan Günnemann, Meng Jiang

In this paper, we present a comprehensive and systematic survey of graph data augmentation that summarizes the literature in a structured manner.

Data Augmentation

Multi-Objective Model Selection for Time Series Forecasting

no code implementations17 Feb 2022 Oliver Borchert, David Salinas, Valentin Flunkert, Tim Januschowski, Stephan Günnemann

By learning a mapping from forecasting models to performance metrics, we show that our method PARETOSELECT is able to accurately select models from the Pareto front -- alleviating the need to train or evaluate many forecasting models for model selection.

Model Selection Time Series +1

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

no code implementations NeurIPS 2021 Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann

We furthermore set the state of the art on ZINC and coordinate-free QM9 by incorporating synthetic coordinates in the SMP and DimeNet++ models.

Molecular Property Prediction

Robustness of Graph Neural Networks at Scale

1 code implementation NeurIPS 2021 Simon Geisler, Tobias Schmidt, Hakan Şirin, Daniel Zügner, Aleksandar Bojchevski, Stephan Günnemann

Graph Neural Networks (GNNs) are increasingly important given their popularity and the diversity of applications.

Intriguing Properties of Input-dependent Randomized Smoothing

no code implementations11 Oct 2021 Peter Súkeník, Aleksei Kuvshinov, Stephan Günnemann

We show that in general, the input-dependent smoothing suffers from the curse of dimensionality, forcing the variance function to have low semi-elasticity.

Fairness

End-to-End Learning of Probabilistic Hierarchies on Graphs

no code implementations ICLR 2022 Daniel Zügner, Bertrand Charpentier, Morgane Ayle, Sascha Geringer, Stephan Günnemann

We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies.

Link Prediction

Locality-Based Mini Batching for Graph Neural Networks

no code implementations29 Sep 2021 Johannes Klicpera, Chendi Qian, Stephan Günnemann

Training graph neural networks on large graphs is challenging since there is no clear way of how to extract mini batches from connected data.

Provably Robust Transfer

no code implementations29 Sep 2021 Anna-Kathrin Kopetzki, Jana Obernosterer, Aleksandar Bojchevski, Stephan Günnemann

Our experiments show how adversarial training on the source domain affects robustness on source and target domain, and we propose the first provably robust transfer learning models.

Adversarial Robustness Transfer Learning

A Study of Joint Graph Inference and Forecasting

no code implementations10 Sep 2021 Daniel Zügner, François-Xavier Aubet, Victor Garcia Satorras, Tim Januschowski, Stephan Günnemann, Jan Gasthaus

We study a recent class of models which uses graph neural networks (GNNs) to improve forecasting in multivariate time series.

Graph Learning Time Series

On Second-order Optimization Methods for Federated Learning

no code implementations6 Sep 2021 Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich

We consider federated learning (FL), where the training data is distributed across a large number of clients.

Federated Learning

Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience (VesselGraph)

1 code implementation30 Aug 2021 Johannes C. Paetzold, Julian McGinnis, Suprosanna Shit, Ivan Ezhov, Paul Büschl, Chinmay Prabhakar, Mihail I. Todorov, Anjany Sekuboyina, Georgios Kaissis, Ali Ertürk, Stephan Günnemann, Bjoern H. Menze

Moreover, we benchmark numerous state-of-the-art graph learning algorithms on the biologically relevant tasks of vessel prediction and vessel classification using the introduced vessel graph dataset.

Graph Learning

OODformer: Out-Of-Distribution Detection Transformer

1 code implementation19 Jul 2021 Rajat Koner, Poulami Sinhamahapatra, Karsten Roscher, Stephan Günnemann, Volker Tresp

A serious problem in image classification is that a trained model might perform well for input data that originates from the same distribution as the data available for model training, but performs much worse for out-of-distribution (OOD) samples.

Contrastive Learning OOD Detection +1

Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More

no code implementations14 Jul 2021 Johannes Gasteiger, Marten Lienen, Stephan Günnemann

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations.

MDE4QAI: Towards Model-Driven Engineering for Quantum Artificial Intelligence

no code implementations14 Jul 2021 Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann

Over the past decade, Artificial Intelligence (AI) has provided enormous new possibilities and opportunities, but also new demands and requirements for software systems.

Code Generation

Graphhopper: Multi-Hop Scene Graph Reasoning for Visual Question Answering

1 code implementation13 Jul 2021 Rajat Koner, Hang Li, Marcel Hildebrandt, Deepan Das, Volker Tresp, Stephan Günnemann

We conduct an experimental study on the challenging dataset GQA, based on both manually curated and automatically generated scene graphs.

Natural Language Processing Question Answering +1

Supporting AI Engineering on the IoT Edge through Model-Driven TinyML

no code implementations6 Jul 2021 Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann

We focus on a sub-discipline of AI, namely Machine Learning (ML) and propose the delegation of data analytics and ML to the IoT edge.

ML-Quadrat & DriotData: A Model-Driven Engineering Tool and a Low-Code Platform for Smart IoT Services

no code implementations6 Jul 2021 Armin Moin, Andrei Mituca, Moharram Challenger, Atta Badii, Stephan Günnemann

In this paper, we present ML-Quadrat, an open-source research prototype that is based on the Eclipse Modeling Framework (EMF) and the state of the art in the literature of Model-Driven Software Engineering (MDSE) for smart Cyber-Physical Systems (CPS) and the Internet of Things (IoT).

A Model-Driven Approach to Machine Learning and Software Modeling for the IoT

1 code implementation6 Jul 2021 Armin Moin, Moharram Challenger, Atta Badii, Stephan Günnemann

In particular, we implement the proposed approach, called ML-Quadrat, based on ThingML, and validate it using a case study from the IoT domain, as well as through an empirical user evaluation.

Decision Making

On Out-of-distribution Detection with Energy-based Models

1 code implementation3 Jul 2021 Sven Elflein, Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data.

Density Estimation OOD Detection +1

Detecting Anomalous Event Sequences with Temporal Point Processes

no code implementations NeurIPS 2021 Oleksandr Shchur, Ali Caner Türkmen, Tim Januschowski, Jan Gasthaus, Stephan Günnemann

Automatically detecting anomalies in event data can provide substantial value in domains such as healthcare, DevOps, and information security.

OOD Detection Point Processes

GemNet: Universal Directional Graph Neural Networks for Molecules

2 code implementations NeurIPS 2021 Johannes Gasteiger, Florian Becker, Stephan Günnemann

Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations.

Translation

Neural Temporal Point Processes: A Review

no code implementations8 Apr 2021 Oleksandr Shchur, Ali Caner Türkmen, Tim Januschowski, Stephan Günnemann

Temporal point processes (TPP) are probabilistic generative models for continuous-time event sequences.

Point Processes

Collective Robustness Certificates

no code implementations ICLR 2021 Jan Schuchardt, Aleksandar Bojchevski, Johannes Klicpera, Stephan Günnemann

In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions (a vector of labels) based on a single input, i. e. a single graph, image, or document respectively.

Adversarial Robustness named-entity-recognition +3

Deep Rao-Blackwellised Particle Filters for Time Series Forecasting

no code implementations NeurIPS 2020 Richard Kurle, Syama Sundar Rangapuram, Emmanuel de Bézenac, Stephan Günnemann, Jan Gasthaus

We propose a Monte Carlo objective that leverages the conditional linearity by computing the corresponding conditional expectations in closed-form and a suitable proposal distribution that is factorised similarly to the optimal proposal distribution.

Time Series Time Series Forecasting

Reliable Graph Neural Networks via Robust Aggregation

1 code implementation NeurIPS 2020 Simon Geisler, Daniel Zügner, Stephan Günnemann

Perturbations targeting the graph structure have proven to be extremely effective in reducing the performance of Graph Neural Networks (GNNs), and traditional defenses such as adversarial training do not seem to be able to improve robustness.

Scalable Normalizing Flows for Permutation Invariant Densities

no code implementations7 Oct 2020 Marin Biloš, Stephan Günnemann

Modeling sets is an important problem in machine learning since this type of data can be found in many domains.

Point Processes

Equivariant Normalizing Flows for Point Processes and Sets

no code implementations28 Sep 2020 Marin Biloš, Stephan Günnemann

To model this behavior, it is enough to transform the samples from the uniform process with a sufficiently complex equivariant function.

Point Processes

From Things' Modeling Language (ThingML) to Things' Machine Learning (ThingML2)

1 code implementation22 Sep 2020 Armin Moin, Stephan Rössler, Marouane Sayih, Stephan Günnemann

In this paper, we illustrate how to enhance an existing state-of-the-art modeling language and tool for the Internet of Things (IoT), called ThingML, to support machine learning on the modeling level.

Code Generation

ThingML+ Augmenting Model-Driven Software Engineering for the Internet of Things with Machine Learning

1 code implementation22 Sep 2020 Armin Moin, Stephan Rössler, Stephan Günnemann

In this paper, we present the current position of the research project ML-Quadrat, which aims to extend the methodology, modeling language and tool support of ThingML - an open source modeling tool for IoT/CPS - to address Machine Learning needs for the IoT applications.

Code Generation

Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More

no code implementations ICML 2020 Aleksandar Bojchevski, Johannes Klicpera, Stephan Günnemann

Existing techniques for certifying the robustness of models for discrete data either work only for a small class of models or are general at the expense of efficiency or tightness.

Deep Representation Learning and Clustering of Traffic Scenarios

no code implementations15 Jul 2020 Nick Harmening, Marin Biloš, Stephan Günnemann

Determining the traffic scenario space is a major challenge for the homologation and coverage assessment of automated driving functions.

Representation Learning

Scene Graph Reasoning for Visual Question Answering

no code implementations2 Jul 2020 Marcel Hildebrandt, Hang Li, Rajat Koner, Volker Tresp, Stephan Günnemann

We propose a novel method that approaches the task by performing context-driven, sequential reasoning based on the objects and their semantic and spatial relationships present in the scene.

Natural Language Processing Question Answering +1

Fast and Flexible Temporal Point Processes with Triangular Maps

1 code implementation NeurIPS 2020 Oleksandr Shchur, Nicholas Gao, Marin Biloš, Stephan Günnemann

Temporal point process (TPP) models combined with recurrent neural networks provide a powerful framework for modeling continuous-time event data.

Point Processes Variational Inference

Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

1 code implementation NeurIPS 2020 Bertrand Charpentier, Daniel Zügner, Stephan Günnemann

The posterior distributions learned by PostNet accurately reflect uncertainty for in- and out-of-distribution data -- without requiring access to OOD data at training time.

OOD Detection

Continual Learning with Bayesian Neural Networks for Non-Stationary Data

no code implementations ICLR 2020 Richard Kurle, Botond Cseke, Alexej Klushyn, Patrick van der Smagt, Stephan Günnemann

We represent the posterior approximation of the network weights by a diagonal Gaussian distribution and a complementary memory of raw data.

Continual Learning

Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs

1 code implementation AKBC 2020 Zhen Han, Yunpu Ma, Yuyi Wang, Stephan Günnemann, Volker Tresp

The Hawkes process has become a standard method for modeling self-exciting event sequences with different event types.

Knowledge Graphs

Certifiable Robustness to Graph Perturbations

1 code implementation NeurIPS 2019 Aleksandar Bojchevski, Stephan Günnemann

Despite the exploding interest in graph neural networks there has been little effort to verify and improve their robustness.

Diffusion Improves Graph Learning

2 code implementations NeurIPS 2019 Johannes Gasteiger, Stefan Weißenberger, Stephan Günnemann

In this work, we remove the restriction of using only the direct neighbors by introducing a powerful, yet spatially localized graph convolution: Graph diffusion convolution (GDC).

Graph Learning Node Classification

Intensity-Free Learning of Temporal Point Processes

2 code implementations ICLR 2020 Oleksandr Shchur, Marin Biloš, Stephan Günnemann

The standard way of learning in such models is by estimating the conditional intensity function.

Point Processes

Certifiable Robustness and Robust Training for Graph Convolutional Networks

1 code implementation28 Jun 2019 Daniel Zügner, Stephan Günnemann

Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable.

Node Classification

Adversarial Attacks on Node Embeddings

no code implementations ICLR 2019 Aleksandar Bojchevski, Stephan Günnemann

The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks.

Representation Learning

Pitfalls of Graph Neural Network Evaluation

1 code implementation14 Nov 2018 Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, Stephan Günnemann

We perform a thorough empirical evaluation of four prominent GNN models and show that considering different splits of the data leads to dramatically different rankings of models.

Graph Mining Node Classification

Multi-Source Neural Variational Inference

no code implementations11 Nov 2018 Richard Kurle, Stephan Günnemann, Patrick van der Smagt

Learning from multiple sources of information is an important problem in machine-learning research.

Variational Inference

Predict then Propagate: Graph Neural Networks meet Personalized PageRank

4 code implementations ICLR 2019 Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann

We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP.

Classification General Classification +1

Mining Contrasting Quasi-Clique Patterns

no code implementations3 Oct 2018 Roberto Alonso, Stephan Günnemann

Mining dense quasi-cliques is a well-known clustering task with applications ranging from social networks over collaboration graphs to document analysis.

Adversarial Attacks on Node Embeddings via Graph Poisoning

1 code implementation ICLR 2019 Aleksandar Bojchevski, Stephan Günnemann

The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks.

Representation Learning

Dual-Primal Graph Convolutional Networks

no code implementations3 Jun 2018 Federico Monti, Oleksandr Shchur, Aleksandar Bojchevski, Or Litany, Stephan Günnemann, Michael M. Bronstein

In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs.

Graph Attention Recommendation Systems

Adversarial Attacks on Neural Networks for Graph Data

1 code implementation21 May 2018 Daniel Zügner, Amir Akbarnejad, Stephan Günnemann

Even more, our attacks are transferable: the learned attacks generalize to other state-of-the-art node classification models and unsupervised approaches, and likewise are successful even when only limited knowledge about the graph is given.

General Classification Node Classification

NetGAN: Generating Graphs via Random Walks

1 code implementation ICML 2018 Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, Stephan Günnemann

NetGAN is able to produce graphs that exhibit well-known network patterns without explicitly specifying them in the model definition.

Graph Generation Link Prediction

Introduction to Tensor Decompositions and their Applications in Machine Learning

1 code implementation29 Nov 2017 Stephan Rabanser, Oleksandr Shchur, Stephan Günnemann

Tensors are multidimensional arrays of numerical values and therefore generalize matrices to multiple dimensions.

Tensor Decomposition

Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking

1 code implementation ICLR 2018 Aleksandar Bojchevski, Stephan Günnemann

We propose Graph2Gauss - an approach that can efficiently learn versatile node embeddings on large scale (attributed) graphs that show strong performance on tasks such as link prediction and node classification.

Link Prediction Network Embedding +1

Linearized and Single-Pass Belief Propagation

1 code implementation27 Jun 2014 Wolfgang Gatterbauer, Stephan Günnemann, Danai Koutra, Christos Faloutsos

Often, we can answer such questions and label nodes in a network based on the labels of their neighbors and appropriate assumptions of homophily ("birds of a feather flock together") or heterophily ("opposites attract").

Cannot find the paper you are looking for? You can Submit a new open access paper.