Search Results for author: Mathias Niepert

Found 59 papers, 23 papers with code

Continual Invariant Risk Minimization

no code implementations21 Oct 2023 Francesco Alesiani, Shujian Yu, Mathias Niepert

Invariant risk minimization (IRM) is a recent proposal for discovering environment-invariant representations.

Continual Learning

Probabilistically Rewired Message-Passing Neural Networks

1 code implementation3 Oct 2023 Chendi Qian, Andrei Manolache, Kareem Ahmed, Zhe Zeng, Guy Van Den Broeck, Mathias Niepert, Christopher Morris

Message-passing graph neural networks (MPNNs) emerged as powerful tools for processing graph-structured input.

Approximate Answering of Graph Queries

no code implementations12 Aug 2023 Michael Cochez, Dimitrios Alivanistos, Erik Arakelyan, Max Berrendorf, Daniel Daza, Mikhail Galkin, Pasquale Minervini, Mathias Niepert, Hongyu Ren

We will first provide an overview of the different query types which can be supported by these methods and datasets typically used for evaluation, as well as an insight into their limitations.

Knowledge Graphs World Knowledge

Learning Disentangled Discrete Representations

1 code implementation26 Jul 2023 David Friede, Christian Reimers, Heiner Stuckenschmidt, Mathias Niepert

Recent successes in image generation, model-based reinforcement learning, and text-to-image generation have demonstrated the empirical advantages of discrete latent representations, although the reasons behind their benefits remain unclear.

Model-based Reinforcement Learning Model Selection

Efficient Learning of Discrete-Continuous Computation Graphs

1 code implementation NeurIPS 2021 David Friede, Mathias Niepert

We analyze the behavior of more complex stochastic computations graphs with multiple sequential discrete components.

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

1 code implementation NeurIPS 2023 Duy M. H. Nguyen, Hoang Nguyen, Nghiem T. Diep, Tan N. Pham, Tri Cao, Binh T. Nguyen, Paul Swoboda, Nhat Ho, Shadi Albarqouni, Pengtao Xie, Daniel Sonntag, Mathias Niepert

While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images.

Contrastive Learning Diabetic Retinopathy Grading +3

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

1 code implementation17 May 2023 Federico Errica, Mathias Niepert

We introduce Graph-Induced Sum-Product Networks (GSPNs), a new probabilistic framework for graph representation learning that can tractably answer probabilistic queries.

Graph Classification Graph Representation Learning

Learning Neural PDE Solvers with Parameter-Guided Channel Attention

2 code implementations27 Apr 2023 Makoto Takamoto, Francesco Alesiani, Mathias Niepert

The experiments also show several advantages of CAPE, such as its increased ability to generalize to unseen PDE parameters without large increases inference time and parameter count.

PDE Surrogate Modeling Weather Forecasting

Learning Sparsity of Representations with Discrete Latent Variables

no code implementations3 Apr 2023 Zhao Xu, Daniel Onoro Rubio, Giuseppe Serra, Mathias Niepert

The resulting sparsity of a representation is not fixed, but fits to the observation itself under the pre-defined restriction.

State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions

no code implementations10 Dec 2022 Cheng Wang, Carolin Lawrence, Mathias Niepert

We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.

Memorization Object Recognition +1

PDEBENCH: An Extensive Benchmark for Scientific Machine Learning

2 code implementations13 Oct 2022 Makoto Takamoto, Timothy Praditia, Raphael Leiteritz, Dan MacKinlay, Francesco Alesiani, Dirk Pflüger, Mathias Niepert

With those metrics we identify tasks which are challenging for recent ML methods and propose these tasks as future challenges for the community.

SIMPLE: A Gradient Estimator for $k$-Subset Sampling

1 code implementation4 Oct 2022 Kareem Ahmed, Zhe Zeng, Mathias Niepert, Guy Van Den Broeck

$k$-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity.

L2XGNN: Learning to Explain Graph Neural Networks

1 code implementation28 Sep 2022 Giuseppe Serra, Mathias Niepert

Graph Neural Networks (GNNs) are a popular class of machine learning models.

Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models

1 code implementation11 Sep 2022 Pasquale Minervini, Luca Franceschi, Mathias Niepert

In this work, we present Adaptive IMLE (AIMLE), the first adaptive gradient estimator for complex discrete distributions: it adaptively identifies the target distribution for IMLE by trading off the density of gradient information with the degree of bias in the gradient estimates.

Ordered Subgraph Aggregation Networks

no code implementations22 Jun 2022 Chendi Qian, Gaurav Rattan, Floris Geerts, Christopher Morris, Mathias Niepert

Numerous subgraph-enhanced graph neural networks (GNNs) have emerged recently, provably boosting the expressive power of standard (message-passing) GNNs.

milIE: Modular & Iterative Multilingual Open Information Extraction

no code implementations ACL 2022 Bhushan Kotnis, Kiril Gashteovski, Daniel Oñoro Rubio, Vanesa Rodriguez-Tembras, Ammar Shaker, Makoto Takamoto, Mathias Niepert, Carolin Lawrence

In contrast, we explore the hypothesis that it may be beneficial to extract triple slots iteratively: first extract easy slots, followed by the difficult ones by conditioning on the easy slots, and therefore achieve a better overall extraction.

Open Information Extraction

AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark

1 code implementation ACL 2022 Niklas Friedrich, Kiril Gashteovski, Mingying Yu, Bhushan Kotnis, Carolin Lawrence, Mathias Niepert, Goran Glavaš

Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner.

Open Information Extraction

VEGN: Variant Effect Prediction with Graph Neural Networks

no code implementations25 Jun 2021 Jun Cheng, Carolin Lawrence, Mathias Niepert

In contrast, we propose VEGN, which models variant effect prediction using a graph neural network (GNN) that operates on a heterogeneous graph with genes and variants.

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions

2 code implementations NeurIPS 2021 Mathias Niepert, Pasquale Minervini, Luca Franceschi

We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components.

Combinatorial Optimization

Explaining Neural Matrix Factorization with Gradient Rollback

1 code implementation12 Oct 2020 Carolin Lawrence, Timo Sztyler, Mathias Niepert

Moreover, we show theoretically that the difference between gradient rollback's influence approximation and the true influence on a model's behavior is smaller than known bounds on the stability of stochastic gradient descent.

Influence Approximation Knowledge Base Completion +1

Answering Complex Queries in Knowledge Graphs with Bidirectional Sequence Encoders

no code implementations6 Apr 2020 Bhushan Kotnis, Carolin Lawrence, Mathias Niepert

Representation learning for knowledge graphs (KGs) has focused on the problem of answering simple link prediction queries.

Knowledge Graphs Link Prediction +1

Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas

no code implementations IJCNLP 2019 Kosuke Akimoto, Takuya Hiraoka, Kunihiko Sadamasa, Mathias Niepert

Most existing relation extraction approaches exclusively target binary relations, and n-ary relation extraction is relatively unexplored.

Relation Extraction

Attending to Future Tokens For Bidirectional Sequence Generation

1 code implementation IJCNLP 2019 Carolin Lawrence, Bhushan Kotnis, Mathias Niepert

Treated as a node in a fully connected graph, a placeholder token can take past and future tokens into consideration when generating the actual output token.

Learning Discrete Structures for Graph Neural Networks

2 code implementations28 Mar 2019 Luca Franceschi, Mathias Niepert, Massimiliano Pontil, Xiao He

With this work, we propose to jointly learn the graph structure and the parameters of graph convolutional networks (GCNs) by approximately solving a bilevel program that learns a discrete probability distribution on the edges of the graph.

Music Genre Recognition Node Classification

RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems

no code implementations26 Mar 2019 Cheng Wang, Mathias Niepert, Hui Li

Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity and data imbalance and learns transferable latent representations for users, items and their interactions.

Domain Adaptation Recommendation Systems +2

MMKG: Multi-Modal Knowledge Graphs

5 code implementations13 Mar 2019 Ye Liu, Hui Li, Alberto Garcia-Duran, Mathias Niepert, Daniel Onoro-Rubio, David S. Rosenblum

We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs.

Knowledge Graphs Link Prediction

State-Regularized Recurrent Neural Networks

no code implementations25 Jan 2019 Cheng Wang, Mathias Niepert

We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.

Language Modelling Memorization +2

Learning Representations of Missing Data for Predicting Patient Outcomes

no code implementations12 Nov 2018 Brandon Malone, Alberto Garcia-Duran, Mathias Niepert

Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches.

Binary Classification Classification +6

Knowledge Graph Completion to Predict Polypharmacy Side Effects

no code implementations22 Oct 2018 Brandon Malone, Alberto García-Durán, Mathias Niepert

The polypharmacy side effect prediction problem considers cases in which two drugs taken individually do not result in a particular side effect; however, when the two drugs are taken in combination, the side effect manifests.

Knowledge Graph Completion

Towards Transparent Neural Network Acceleration

no code implementations19 Oct 2018 Nicolas Weber, Mathias Niepert, Felipe Huici

While the efficiency problem can be partially addressed with specialized hardware and its corresponding proprietary libraries, we believe that neural network acceleration should be transparent to the user and should support all hardware platforms and deep learning libraries.

object-detection Object Detection

State-Regularized Recurrent Networks

no code implementations27 Sep 2018 Cheng Wang, Mathias Niepert

We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.


Learning Sequence Encoders for Temporal Knowledge Graph Completion

3 code implementations EMNLP 2018 Alberto García-Durán, Sebastijan Dumančić, Mathias Niepert

In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations.

Link Prediction Temporal Knowledge Graph Completion

LRMM: Learning to Recommend with Missing Modalities

no code implementations EMNLP 2018 Cheng Wang, Mathias Niepert, Hui Li

More importantly, LRMM is more robust to previous methods in alleviating data-sparsity and the cold-start problem.

Recommendation Systems

Contextual Hourglass Networks for Segmentation and Density Estimation

no code implementations8 Jun 2018 Daniel Oñoro-Rubio, Mathias Niepert

These shortcut connections improve the performance and it is hypothesized that this is due to mitigating effects on the vanishing gradient problem and the ability of the model to combine feature maps from earlier and later layers.

Density Estimation Image Segmentation +4

Learning Short-Cut Connections for Object Counting

no code implementations8 May 2018 Daniel Oñoro-Rubio, Mathias Niepert, Roberto J. López-Sastre

Standard short-cut connections are connections between layers in deep neural networks which skip at least one intermediate layer.

Density Estimation Object Counting

Towards a Spectrum of Graph Convolutional Networks

no code implementations4 May 2018 Mathias Niepert, Alberto Garcia-Duran

We present our ongoing work on understanding the limitations of graph convolutional networks (GCNs) as well as our work on generalizations of graph convolutions for representing more complex node attribute dependencies.

BrainSlug: Transparent Acceleration of Deep Learning Through Depth-First Parallelism

no code implementations23 Apr 2018 Nicolas Weber, Florian Schmidt, Mathias Niepert, Felipe Huici

Neural network frameworks such as PyTorch and TensorFlow are the workhorses of numerous machine learning applications ranging from object recognition to machine translation.

Machine Translation Object Recognition +1

Representation Learning for Resource Usage Prediction

no code implementations2 Feb 2018 Florian Schmidt, Mathias Niepert, Felipe Huici

Creating a model of a computer system that can be used for tasks such as predicting future resource usage and detecting anomalies is a challenging problem.

Anomaly Detection Representation Learning

TransRev: Modeling Reviews as Translations from Users to Items

no code implementations30 Jan 2018 Alberto Garcia-Duran, Roberto Gonzalez, Daniel Onoro-Rubio, Mathias Niepert, Hui Li

This is exploited in sentiment analysis where machine learning models are used to predict the review score from the text of the review.

Product Recommendation Recommendation Systems +4

Learning Graph Representations with Embedding Propagation

no code implementations NeurIPS 2017 Alberto Garcia-Duran, Mathias Niepert

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data.

KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features

2 code implementations14 Sep 2017 Alberto Garcia-Duran, Mathias Niepert

We present KBLRN, a framework for end-to-end learning of knowledge base representations from latent, relational, and numerical features.

Knowledge Base Completion Representation Learning

Net2Vec: Deep Learning for the Network

no code implementations10 May 2017 Roberto Gonzalez, Filipe Manco, Alberto Garcia-Duran, Jose Mendes, Felipe Huici, Saverio Niccolini, Mathias Niepert

We present Net2Vec, a flexible high-performance platform that allows the execution of deep learning algorithms in the communication network.

General Classification Traffic Classification

Discriminative Gaifman Models

no code implementations NeurIPS 2016 Mathias Niepert

We present discriminative Gaifman models, a novel family of relational machine learning models.

BIG-bench Machine Learning Link Prediction +1

Lifted Probabilistic Inference for Asymmetric Graphical Models

no code implementations1 Dec 2014 Guy Van den Broeck, Mathias Niepert

Lifted probabilistic inference algorithms have been successfully applied to a large number of symmetric graphical models.

Markov Chains on Orbits of Permutation Groups

no code implementations9 Aug 2014 Mathias Niepert

Thus, we present the first lifted MCMC algorithm for probabilistic graphical models.

On the Conditional Independence Implication Problem: A Lattice-Theoretic Approach

no code implementations9 Aug 2014 Mathias Niepert, Dirk Van Gucht, Marc Gyssens

A lattice-theoretic framework is introduced that permits the study of the conditional independence (CI) implication problem relative to the class of discrete probability measures.

Exchangeable Variable Models

no code implementations2 May 2014 Mathias Niepert, Pedro Domingos

A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations.

Tractability through Exchangeability: A New Perspective on Efficient Probabilistic Inference

no code implementations7 Jan 2014 Mathias Niepert, Guy Van Den Broeck

We develop a theory of finite exchangeability and its relation to tractable probabilistic inference.

Symmetry-Aware Marginal Density Estimation

no code implementations9 Apr 2013 Mathias Niepert

The Rao-Blackwell theorem is utilized to analyze and improve the scalability of inference in large probabilistic models that exhibit symmetries.

Density Estimation

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