WebSHAP: Towards Explaining Any Machine Learning Models Anywhere

Abstract

As machine learning (ML) is increasingly integrated into our everyday Web experience, there is a call for transparent and explainable web-based ML. However, existing explainability techniques often require dedicated backend servers, which limit their usefulness as the Web community moves toward in-browser ML for lower latency and greater privacy. To address the pressing need for a client-side explainability solution, we present WebSHAP, the first in-browser tool that adapts the state-of-the-art model-agnostic explainability technique SHAP to the Web environment. Our open-source tool is developed with modern Web technologies such as WebGL that leverage client-side hardware capabilities and make it easy to integrate into existing Web ML applications. We demonstrate WebSHAP in a usage scenario of explaining ML-based loan approval decisions to loan applicants. Reflecting on our work, we discuss the opportunities and challenges for future research on transparent Web ML. WebSHAP is available at https://github.com/poloclub/webshap.

arXiv comment5 pages, 4 figures. Accepted at the ACM Web Conference 2023 (WWW 2023). For a live demo, visit https://poloclub.github.io/webshap/. Code is open-source at https://github.com/poloclub/webshap

References in corpus (9)

• XGBoost: A Scalable Tree Boosting System
• The What-If Tool: Interactive Probing of Machine Learning Models
• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
• Understanding Global Feature Contributions With Additive Importance Measures
• TensorFlow.js: Machine Learning for the Web and Beyond
• Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations
• TimberTrek: Exploring and Curating Sparse Decision Trees with Interactive Visualization
• Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values

Cited by in corpus (1)

• MeMemo: On-device Retrieval Augmentation for Private and Personalized Text Generation