Classification models learn to generalize the associations between data samples and their target classes. However, researchers have increasingly observed that machine learning practice easily leads to systematic errors in AI applications, a phenomenon referred to as “AI blindspots.” Such blindspots arise when a model is trained with training samples (e.g., cat/dog classification) where important patterns (e.g., black cats) are missing or periphery/undesirable patterns (e.g., dogs with grass background) are misleading towards a certain class. Even more sophisticated techniques cannot guarantee to capture, reason about, and prevent the spurious associations. In this work, we propose ESCAPE, a visual analytic system that promotes a human-in-the-loop workflow for countering systematic errors. By allowing human users to easily inspect spurious associations, the system facilitates users to spontaneously recognize concepts associated misclassifications and evaluate mitigation strategies that can reduce biased associations. We also propose two statistical approaches, relative concept association to better quantify the associations between a concept and instances, and debias method to mitigate spurious associations. We demonstrate the utility of our proposed ESCAPE system and statistical measures through extensive evaluation including quantitative experiments, usage scenarios, expert interviews, and controlled user experiments.

Graphs are a ubiquitous data structure to model processes and relations in a wide range of domains. Examples include control-flow graphs in programs and semantic scene graphs in images. Identifying subgraph patterns in graphs is an important approach to understand their structural properties. We propose a visual analytics system GraphQ to support human-in-the-loop, example-based, subgraph pattern search in a database containing many individual graphs. To support fast, interactive queries, we use graph neural networks (GNNs) to encode a graph as fixed-length latent vector representation, and perform subgraph matching in the latent space. Due to the complexity of the problem, it is still difficult to obtain accurate one-to-one node correspondences in the matching results that are crucial for visualization and interpretation. We, therefore, propose a novel GNN for node-alignment called NeuroAlign, to facilitate easy validation and interpretation of the query results. GraphQ provides a visual query interface with a query editor and a multi-scale visualization of the results, as well as a user feedback mechanism for refining the results with additional constraints. We demonstrate GraphQ through two example usage scenarios: analyzing reusable subroutines in program workflows and semantic scene graph search in images. Quantitative experiments show that NeuroAlign achieves 19%-29% improvement in node-alignment accuracy compared to baseline GNN and provides up to 100× speedup compared to combinatorial algorithms. Our qualitative study with domain experts confirms the effectiveness for both usage scenarios.

Bipartite graphs model the key relations in many large scale real-world data: customers purchasing items, legislators voting for bills, people's affiliation with different social groups, faults occurring in vehicles, etc. However, it is challenging to visualize large scale bipartite graphs with tens of thousands or even more nodes or edges. In this paper, we propose a novel visual summarization technique for bipartite graphs based on the minimum description length (MDL) principle. The method simultaneously groups the two different set of nodes and constructs aggregated bipartite relations with balanced granularity and precision. It addresses the key trade-off that often occurs for visualizing large scale and noisy data: acquiring a clear and uncluttered overview while maximizing the information content in it. We formulate the visual summarization task as a co-clustering problem and propose an efficient algorithm based on locality sensitive hashing (LSH) that can easily scale to large graphs under reasonable interactive time constraints that previous related methods cannot satisfy. The method leads to the opportunity of introducing a visual analytics framework with multiple levels-of-detail to facilitate interactive data exploration. In the framework, we also introduce a compact visual design inspired by adjacency list representation of graphs as the building block for a small multiples display to compare the bipartite relations for different subsets of data. We showcase the applicability and effectiveness of our approach by applying it on synthetic data with ground truth and performing case studies on real-world datasets from two application domains including roll-call vote record analysis and vehicle fault pattern analysis. Interviews with experts in the political science community and the automotive industry further highlight the benefits of our approach.

Shadow aliasing due to limited storage precision has been plaguing discrete shadowing algorithms for decades. We present a simple method to eliminate false self-shadowing through adaptive depth bias. Unlike existing methods which simply set the weight of the bias based on surface slope or utilize the second nearest surface, we evaluate the bound of bias for each fragment and compute the optimal bias within the bound. Our method introduces small overhead, preserves more shadow details than widely used constant bias and slope scale bias and works for common 2D shadow maps as well as 3D binary shadow volumes.

Rough refraction commonly occurs when light scatters on rough transparent surfaces. It presents a computational challenge, as every pixel's color depends on incoming light from numerous directions. De Rousiers et al. [2011] compute rough refraction interactively using a convolution of Gaussian normal and transmittance distribution functions (NDFs and BTDFs), but their work is limited to a constant roughness surfaces. We introduce two methods that allow for varying roughness by representing surface normals using LEAN mapping and Gaussian sum reduction (GSR).