VISPUR: Visual Aids for Identifying and Interpreting Spurious Associations in Data-Driven Decisions
Big data and machine learning tools have jointly empowered humans in making data-driven decisions. However, many of them capture empirical associations that might be spurious due to confounding factors and subgroup heterogeneity. The famous Simpson's paradox is such a phenomenon where aggregated and subgroup-level associations contradict with each other, causing cognitive confusions and difficulty in making adequate interpretations and decisions. Existing tools provide little insights for humans to locate, reason about, and prevent pitfalls of spurious association in practice. We propose VISPUR, a visual analytic system that provides a causal analysis framework and a human-centric workflow for tackling spurious associations. These include a CONFOUNDER DASHBOARD, which can automatically identify possible confounding factors, and a SUBGROUP VIEWER, which allows for the visualization and comparison of diverse subgroup patterns that likely or potentially result in a misinterpretation of causality. Additionally, we propose a REASONING STORYBOARD, which uses a flow-based approach to illustrate paradoxical phenomena, as well as an interactive DECISION DIAGNOSIS panel that helps ensure accountable decision-making. Through an expert interview and a controlled user experiment, our qualitative and quantitative results demonstrate that the proposed "de-paradox" workflow and the designed visual analytic system are effective in helping human users to identify and understand spurious associations, as well as to make accountable causal decisions.
Code (1)
Tasks
Decision MakingSimilar Papers 제목 키워드 기반
Invariant representation learning for sequential recommendation
Sequential recommendation involves automatically recommending the next item to users based on their historical item sequence. While most prior research employs RNN or transformer methods to glean information from the ite…
Representation LearningSequential RecommendationIdentifying Spurious Correlations using Counterfactual Alignment
Models driven by spurious correlations often yield poor generalization performance. We propose the counterfactual (CF) alignment method to detect and quantify spurious correlations of black box classifiers. Our methodolo…
AttributecounterfactualAttributionScanner: A Visual Analytics System for Model Validation with Metadata-Free Slice Finding
Data slice finding is an emerging technique for validating machine learning (ML) models by identifying and analyzing subgroups in a dataset that exhibit poor performance, often characterized by distinct feature sets or d…
DescriptiveInterpreting and Controlling Vision Foundation Models via Text Explanations
Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to their black-box nature, understanding the underlying rules behind these models' pre…
Model EditingVisual ReasoningIdentifying Spurious Correlations and Correcting them with an Explanation-based Learning
Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learne…
Classificationimage-classificationImage Classification