Active learning (AL) reduces the amount of labeled data needed to train ...
We perform the first adversarial robustness study into Graph Neural Netw...
Several architecture frameworks for software, systems, and enterprises h...
The ability to detect learned objects regardless of their appearance is
...
Machine Learning (ML) models in Robotic Assembly Sequence Planning (RASP...
Despite its success in the image domain, adversarial training does not (...
Graph Neural Networks (GNNs) are promising surrogates for quantum mechan...
Recent advances in machine learning for molecules exhibit great potentia...
Graph Neural Networks (GNNs) have become the de-facto standard tool for
...
Many works show that node-level predictions of Graph Neural Networks (GN...
Emerging quantum computing technologies, such as Noisy Intermediate-Scal...
Bayesian inference in deep neural networks is challenging due to the
hig...
Modern machine learning models have started to consume incredible amount...
Accurate and efficient uncertainty estimation is crucial to build reliab...
Neural architectures that learn potential energy surfaces from molecular...
Recent neural network-based wave functions have achieved state-of-the-ar...
In tasks like node classification, image segmentation, and named-entity
...
Transformers were originally proposed as a sequence-to-sequence model fo...
A cursory reading of the literature suggests that we have made a lot of
...
Randomized smoothing is one of the most promising frameworks for certify...
Deep learning models are known to put the privacy of their training data...
Using graph neural networks for large graphs is challenging since there ...
Building models that comply with the invariances inherent to different
d...
Temporal data like time series are often observed at irregular intervals...
Models for image segmentation, node classification and many other tasks ...
We introduce an ODE solver for the PyTorch ecosystem that can solve mult...
Observations made in continuous time are often irregular and contain the...
A powerful framework for studying graphs is to consider them as geometri...
Node embedding methods map network nodes to low dimensional vectors that...
In this paper, we propose to adopt the MDE paradigm for the development ...
There is a widespread belief that the tone of US political language has
...
The robustness and anomaly detection capability of neural networks are
c...
Pruning, the task of sparsifying deep neural networks, received increasi...
Characterizing aleatoric and epistemic uncertainty on the predicted rewa...
Obtaining the energy of molecular systems typically requires solving the...
Single-cell transcriptomics enabled the study of cellular heterogeneity ...
The predominant method of demonstrating progress of atomic graph neural
...
We propose a new method for spatio-temporal forecasting on arbitrarily
d...
It is essential for safety-critical applications of deep neural networks...
We propose a new differentiable probabilistic model over DAGs (DP-DAG).
...
Developing smart software services requires both Software Engineering an...
Data augmentation has recently seen increased interest in graph machine
...
Research on time series forecasting has predominantly focused on develop...
Graph neural networks that leverage coordinates via directional message
...
Graph Neural Networks (GNNs) are increasingly important given their
popu...
The interdependence between nodes in graphs is key to improve class
pred...
Neural ordinary differential equations describe how values change in tim...
End-to-end (geometric) deep learning has seen first successes in
approxi...
Randomized smoothing is currently considered the state-of-the-art method...
Solving the Schrödinger equation is key to many quantum mechanical
prope...