With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. It uses a graphical causal model to represent causal relationships among different features in the dataset and as a medium to inject domain knowledge. A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics. Thereafter, the user can mitigate bias by refining the causal model and acting on the unfair causal edges. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset based on the current causal model while ensuring a minimal change from the original dataset. Users can visually assess the impact of their interactions on different fairness metrics, utility metrics, data distortion, and the underlying data distribution. Once satisfied, they can download the debiased dataset and use it for any downstream application for fairer predictions. We evaluate D-BIAS by conducting experiments on 3 datasets and also a formal user study. We found that D-BIAS helps reduce bias significantly compared to the baseline debiasing approach across different fairness metrics while incurring little data distortion and a small loss in utility. Moreover, our human-in-the-loop based approach significantly outperforms an automated approach on trust, interpretability and accountability.

Cluster analysis (CA) is a powerful strategy for the exploration of high-dimensional data in the absence of a-priori hypotheses or data classification models, and the results of CA can then be used to form such models. But even though formal models and classification rules may not exist in these data exploration scenarios, domain scientists and experts generally have a vast amount of non-compiled knowledge and intuition that they can bring to bear in this effort. In CA, there are various popular mechanisms to generate the clusters, however, the results from their non- supervised deployment rarely fully agree with this expert knowledge and intuition. To this end, our paper describes a comprehensive and intuitive framework to aid scientists in the derivation of classification hierarchies in CA, using k-means as the overall clustering engine, but allowing them to tune its parameters interactively based on a non-distorted compact visual presentation of the inherent characteristics of the data in high- dimensional space. These include cluster geometry, composition, spatial relations to neighbors, and others. In essence, we provide all the tools necessary for a high-dimensional activity we call cluster sculpting, and the evolving hierarchy can then be viewed in a space-efficient radial dendrogram. We demonstrate our system in the context of the mining and classification of a large collection of millions of data items of aerosol mass spectra, but our framework readily applies to any high-dimensional CA scenario.

Anomalous runtime behavior detection is one of the most important tasks for performance diagnosis in High Performance Computing (HPC). Most of the existing methods find anomalous executions based on the properties of individual functions, such as execution time. However, it is insufficient to identify abnormal behavior without taking into account the context of the executions, such as the invocations of children functions and the communications with other HPC nodes. We improve upon the existing anomaly detection approaches by utilizing the call stack structures of the executions, which record rich temporal and contextual information. With our call stack tree (CSTree) representation of the executions, we formulate the anomaly detection problem as finding anomalous tree structures in a call stack forest. The CSTrees are converted to vector representations using our proposed stack2vec embedding. Structural and temporal visualizations of CSTrees are provided to support users in the identification and verification of the anomalies during an active anomaly detection process. Three case studies of real-world HPC applications demonstrate the capabilities of our approach.