Related papers: Interpretable Diversity Analysis: Visualizing Feat…
Interpreting the decision logic behind effective deep convolutional neural networks (CNN) on images complements the success of deep learning models. However, the existing methods can only interpret some specific decision logic on individual…
Deep learning architectures have proved versatile in a number of drug discovery applications, including the modelling of in vitro compound activity. While controlling for prediction confidence is essential to increase the trust,…
The combination of multiple classifiers using ensemble methods is increasingly important for making progress in a variety of difficult prediction problems. We present a comparative analysis of several ensemble methods through two case…
While ensembling deep neural networks has shown promise in improving generalization performance, scaling current ensemble methods for large models remains challenging. Given that recent progress in deep learning is largely driven by the…
Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing constraints on the model, often at the expense of predictive…
For an ensemble of data points in a multi-parameter space, we present a visual analytics technique to select a representative distribution of parameter values, and analyse how representative this distribution is in all ensemble members. A…
The increasing impact of black box models, and particularly of unsupervised ones, comes with an increasing interest in tools to understand and interpret them. In this paper, we consider in particular how to characterise visual groupings…
While machine-learning models are flourishing and transforming many aspects of everyday life, the inability of humans to understand complex models poses difficulties for these models to be fully trusted and embraced. Thus, interpretability…
For many practical, high-risk applications, it is essential to quantify uncertainty in a model's predictions to avoid costly mistakes. While predictive uncertainty is widely studied for neural networks, the topic seems to be under-explored…
A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…
Developing a suitable Deep Neural Network (DNN) often requires significant iteration, where different model versions are evaluated and compared. While metrics such as accuracy are a powerful means to succinctly describe a model's…
Nonlinear system identification often involves a fundamental trade-off between interpretability and flexibility, often requiring the incorporation of physical constraints. We propose a unified data-driven framework that combines the…
This paper presents an ensemble forecasting method that shows strong results on the M4 Competition dataset by decreasing feature and model selection assumptions, termed DONUT (DO Not UTilize human beliefs). Our assumption reductions,…
In person re-identification (re-ID), the key task is feature representation, which is used to compute distance or similarity in prediction. Person re-ID achieves great improvement when deep learning methods are introduced to tackle this…
In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We investigate the potential of an attribution-based diversity…
Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This…
How do two deep neural networks differ in how they arrive at a decision? Measuring the similarity of deep networks has been a long-standing open question. Most existing methods provide a single number to measure the similarity of two…
The analysis of complex high-dimensional data is a common task in many domains, resulting in bespoke visual exploration tools. Expectations and practices of domain experts as users do not always align with visualization theory. In this…
Graph neural networks (GNNs) demonstrate great performance in compound property and activity prediction due to their capability to efficiently learn complex molecular graph structures. However, two main limitations persist including…
Deep ensembles have been empirically shown to be a promising approach for improving accuracy, uncertainty and out-of-distribution robustness of deep learning models. While deep ensembles were theoretically motivated by the bootstrap,…