2.7k citations · 4k across the 68 of their papers we have counts for
37 papers · 1 filter
Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data
Kevin Kasa, Graham W. Taylor
Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to d…
Bounding generalization error with input compression: An empirical study with infinite-width networks
Angus Galloway, Anna Golubeva, Mahmoud Salem +3
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data. The ability to better predict GE ba…
Monitoring Shortcut Learning using Mutual Information
Mohammed Adnan, Yani Ioannou, Chuan-Yung Tsai +3
The failure of deep neural networks to generalize to out-of-distribution data is a well-known problem and raises concerns about the deployment of trained networks in safety-critica…
On Evaluation Metrics for Graph Generative Models
Rylee Thompson, Boris Knyazev, Elahe Ghalebi +2
In image generation, generative models can be evaluated naturally by visually inspecting model outputs. However, this is not always the case for graph generative models (GGMs), mak…
Domain-Agnostic Clustering with Self-Distillation
Mohammed Adnan, Yani A. Ioannou, Chuan-Yung Tsai +1
Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning. However, most self-supervised and deep clustering…
Empirical analysis of representation learning and exploration in neural kernel bandits
Michal Lisicki, Arash Afkanpour, Graham W. Taylor
Neural bandits have been shown to provide an efficient solution to practical sequential decision tasks that have nonlinear reward functions. The main contributor to that success is…
Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning
Hyunsoo Chung, Jungtaek Kim, Boris Knyazev +4
Discovering a solution in a combinatorial space is prevalent in many real-world problems but it is also challenging due to diverse complex constraints and the vast number of possib…
Parameter Prediction for Unseen Deep Architectures
Boris Knyazev, Michal Drozdzal, Graham W. Taylor +1
Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely ha…
Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization
Michal Lisicki, Arash Afkanpour, Graham W. Taylor
Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems. The field recently e…
Neuron-based explanations of neural networks sacrifice completeness and interpretability
Nolan Dey, Eric Taylor, Alexander Wong +2
High quality explanations of neural networks (NNs) should exhibit two key properties. Completeness ensures that they accurately reflect a network's function and interpretability ma…
Enabling Continual Learning with Differentiable Hebbian Plasticity
Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor
Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge. However, catastrophic forgetting poses a grand cha…
Sample-Efficient Model-based Actor-Critic for an Interactive Dialogue Task
Katya Kudashkina, Valliappa Chockalingam, Graham W. Taylor +1
Human-computer interactive systems that rely on machine learning are becoming paramount to the lives of millions of people who use digital assistants on a daily basis. Yet, further…
Learning Permutation Invariant Representations using Memory Networks
Shivam Kalra, Mohammed Adnan, Graham Taylor +1
Many real-world tasks such as classification of digital histopathology images and 3D object detection involve learning from a set of instances. In these cases, only a group of inst…
A Nonparametric Bayesian Model for Sparse Dynamic Multigraphs
Elahe Ghalebi, Hamidreza Mahyar, Radu Grosu +2
As the availability and importance of temporal interaction data--such as email communication--increases, it becomes increasingly important to understand the underlying structure th…
Batch Normalization is a Cause of Adversarial Vulnerability
Angus Galloway, Anna Golubeva, Thomas Tanay +2
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks. In many cases it indeed decreases the number of parameter…
Understanding Attention and Generalization in Graph Neural Networks
Boris Knyazev, Graham W. Taylor, Mohamed R. Amer
We aim to better understand attention over nodes in graph neural networks (GNNs) and identify factors influencing its effectiveness. We particularly focus on the ability of attenti…
Beyond Explainability: Leveraging Interpretability for Improved Adversarial Learning
Devinder Kumar, Ibrahim Ben-Daya, Kanav Vats +3
In this study, we propose the leveraging of interpretability for tasks beyond purely the purpose of explainability. In particular, this study puts forward a novel strategy for leve…
Adversarial Examples as an Input-Fault Tolerance Problem
Angus Galloway, Anna Golubeva, Graham W. Taylor
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e.…
Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
Boris Knyazev, Xiao Lin, Mohamed R. Amer +1
Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful…
Self-Paced Learning with Adaptive Deep Visual Embeddings
Vithursan Thangarasa, Graham W. Taylor
Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore…
Stochastic Layer-Wise Precision in Deep Neural Networks
Griffin Lacey, Graham W. Taylor, Shawki Areibi
Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low pr…
Quantitatively Evaluating GANs With Divergences Proposed for Training
Daniel Jiwoong Im, He Ma, Graham Taylor +1
Generative adversarial networks (GANs) have been extremely effective in approximating complex distributions of high-dimensional, input data samples, and substantial progress has be…
Generalized Hadamard-Product Fusion Operators for Visual Question Answering
Brendan Duke, Graham W. Taylor
We propose a generalized class of multimodal fusion operators for the task of visual question answering (VQA). We identify generalizations of existing multimodal fusion operators b…
Convolutional Neural Networks Regularized by Correlated Noise
Shamak Dutta, Bryan Tripp, Graham Taylor
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In…