ML Infra + Apps
FastCFE: A counterfactual explainer using reinforcement learning
Ray Summit 2022
Counterfactuals, an active area of research in machine learning explainability, are explanations that produce actionable steps to move a data point from one side of a decision boundary to another. These explanations have a clear use case for several applications ranging from loan decisions to healthcare diagnosis, where they need to advise stakeholders about actions they can take to achieve a different outcome. Individuals not provided loans want steps they can take to achieve a loan, and similarly patients want to know how they can achieve a better diagnosis. This presentation showcases FastCFE, an algorithm and feature that uses reinforcement learning to provide real-time counterfactual explanations. Our presentation is broken down as follows:
- Overview of counterfactuals and reinforcement learning (RL)
- Deep distributed reinforcement learning using OpenAI Gym and Ray+RLlib and a demonstration using these frameworks.
- Benchmarks and results
About Karthik
Karthik Rao is a machine learning engineer at Arthur AI (Monitoring, Performance, Explainability). He was previously an undergraduate at Harvard focused on big data systems for machine learning. He is passionate about designing and building novel machine learning solutions using state-of-the art frameworks.
About Sahil
Sahil Verma is a PhD student in the Paul G. Allen School of Computer Science and Engineering at the University of Washington, Seattle. He is interested in exploring ways to make machine learning trustworthy, including explainability and fairness, and he hopes to continue exploring this area in the future.
Karthik Rao
Machine Learning Engineer, Arthur AI
Sahil Verma
PhD Student, University of Washington
Ready to Register?
Come connect with the global community of thinkers and disruptors who are building and deploying the next generation of AI and ML applications.
Save your spot
