Search

As the complexity of machine learning (ML) models increases and their application in different (and critical) domains grows, there is a strong demand for more interpretable and trustworthy ML. A direct, model-agnostic, way to interpret such models is to train surrogate models-such as rule sets and decision trees-that sufficiently approximate the original ones while being simpler and easier-to-explain. Yet, rule sets can become very lengthy, with many if-else statements, and decision tree depth grows rapidly when accurately emulating complex ML models. In such cases, both approaches can fail to meet their core goal-providing users with model interpretability. To tackle this, we propose DeforestVis, a visual analytics tool that offers summarization of the behaviour of complex ML models by providing surrogate decision stumps (one-level decision trees) generated with the Adaptive Boosting (AdaBoost) technique. DeforestVis helps users to explore the complexity versus fidelity trade-off by incrementally generating more stumps, creating attribute-based explanations with weighted stumps to justify decision making, and analysing the impact of rule overriding on training instance allocation between one or more stumps. An independent test set allows users to monitor the effectiveness of manual rule changes and form hypotheses based on case-by-case analyses. We show the applicability and usefulness of DeforestVis with two use cases and expert interviews with data analysts and model developers., Comment: This manuscript is accepted for publication in Computer Graphics Forum (CGF)

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

Applying dimensionality reduction (DR) to large, high-dimensional data sets can be challenging when distinguishing the underlying high-dimensional data clusters in a 2D projection for exploratory analysis. We address this problem by first sharpening the clusters in the original high-dimensional data prior to the DR step using Local Gradient Clustering (LGC). We then project the sharpened data from the high-dimensional space to 2D by a user-selected DR method. The sharpening step aids this method to preserve cluster separation in the resulting 2D projection. With our method, end-users can label each distinct cluster to further analyze an otherwise unlabeled data set. Our `High-Dimensional Sharpened DR' (HD-SDR) method, tested on both synthetic and real-world data sets, is favorable to DR methods with poor cluster separation and yields a better visual cluster separation than these DR methods with no sharpening. Our method achieves good quality (measured by quality metrics) and scales computationally well with large high-dimensional data. To illustrate its concrete applications, we further apply HD-SDR on a recent astronomical catalog., Comment: This paper has been accepted for Information Visualization

Training deep neural networks is challenging when large and annotated datasets are unavailable. Extensive manual annotation of data samples is time-consuming, expensive, and error-prone, notably when it needs to be done by experts. To address this issue, increased attention has been devoted to techniques that propagate uncertain labels (also called pseudo labels) to large amounts of unsupervised samples and use them for training the model. However, these techniques still need hundreds of supervised samples per class in the training set and a validation set with extra supervised samples to tune the model. We improve a recent iterative pseudo-labeling technique, Deep Feature Annotation (DeepFA), by selecting the most confident unsupervised samples to iteratively train a deep neural network. Our confidence-based sampling strategy relies on only dozens of annotated training samples per class with no validation set, considerably reducing user effort in data annotation. We first ascertain the best configuration for the baseline -- a self-trained deep neural network -- and then evaluate our confidence DeepFA for different confidence thresholds. Experiments on six datasets show that DeepFA already outperforms the self-trained baseline, but confidence DeepFA can considerably outperform the original DeepFA and the baseline.

A major issue in Smoothed Particle Hydrodynamics (SPH) approaches is the numerical dissipation during the projection process, especially under coarse discretizations. High-frequency details, such as turbulence and vortices, are smoothed out, leading to unrealistic results. To address this issue, we introduce a Vorticity Refinement (VR) solver for SPH fluids with negligible computational overhead. In this method, the numerical dissipation of the vorticity field is recovered by the difference between the theoretical and the actual vorticity, so as to enhance turbulence details. Instead of solving the Biot-Savart integrals, a stream function, which is easier and more efficient to solve, is used to relate the vorticity field to the velocity field. We obtain turbulence effects of different intensity levels by changing an adjustable parameter. Since the vorticity field is enhanced according to the curl field, our method can not only amplify existing vortices, but also capture additional turbulence. Our VR solver is straightforward to implement and can be easily integrated into existing SPH methods.

Dimensionality reduction methods, also known as projections, are frequently used for exploring multidimensional data in machine learning, data science, and information visualization. Among these, t-SNE and its variants have become very popular for their ability to visually separate distinct data clusters. However, such methods are computationally expensive for large datasets, suffer from stability problems, and cannot directly handle out-of-sample data. We propose a learning approach to construct such projections. We train a deep neural network based on a collection of samples from a given data universe, and their corresponding projections, and next use the network to infer projections of data from the same, or similar, universes. Our approach generates projections with similar characteristics as the learned ones, is computationally two to three orders of magnitude faster than SNE-class methods, has no complex-to-set user parameters, handles out-of-sample data in a stable manner, and can be used to learn any projection technique. We demonstrate our proposal on several real-world high dimensional datasets from machine learning.