Search Results for author:
Found 19 papers, 11 papers with code
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
However, the diverse patterns for coupling parameters, such as residual connections and group convolutions, the diverse deep learning frameworks, and the various time stages at which pruning can be performed make existing pruning methods less adaptable to different architectures, frameworks, and pruning criteria.
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.
Uncertainty Estimation for Molecules: Desiderata and Methods
Graph Neural Networks (GNNs) are promising surrogates for quantum mechanical calculations as they establish unprecedented low errors on collections of molecular dynamics (MD) trajectories.
Edge Directionality Improves Learning on Heterophilic Graphs
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data.
Accuracy is not the only Metric that matters: Estimating the Energy Consumption of Deep Learning Models
Modern machine learning models have started to consume incredible amounts of energy, thus incurring large carbon footprints (Strubell et al., 2019).
Training, Architecture, and Prior for Deterministic Uncertainty Methods
Accurate and efficient uncertainty estimation is crucial to build reliable Machine Learning (ML) models capable to provide calibrated uncertainty estimates, generalize and detect Out-Of-Distribution (OOD) datasets.
On the Robustness and Anomaly Detection of Sparse Neural Networks
The robustness and anomaly detection capability of neural networks are crucial topics for their safe adoption in the real-world.
Winning the Lottery Ahead of Time: Efficient Early Network Pruning
Pruning, the task of sparsifying deep neural networks, received increasing attention recently.
Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning
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.
Differentiable DAG Sampling
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.
Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
GPN outperforms existing approaches for uncertainty estimation in the experiments.
End-to-End Learning of Probabilistic Hierarchies on Graphs
We propose a novel probabilistic model over hierarchies on graphs obtained by continuous relaxation of tree-based hierarchies.
On Out-of-distribution Detection with Energy-based Models
Several density estimation methods have shown to fail to detect out-of-distribution (OOD) samples by assigning higher likelihoods to anomalous data.
Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions
Uncertainty awareness is crucial to develop reliable machine learning models.
Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?
Dirichlet-based uncertainty (DBU) models are a recent and promising class of uncertainty-aware models.
Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
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.
Uncertainty on Asynchronous Time Event Prediction
Asynchronous event sequences are the basis of many applications throughout different industries.
Learning Graph Representations by Dendrograms
Hierarchical graph clustering is a common technique to reveal the multi-scale structure of complex networks.
Hierarchical Graph Clustering using Node Pair Sampling
We present a novel hierarchical graph clustering algorithm inspired by modularity-based clustering techniques.
