Amortized Generation of Sequential Counterfactual Explanations for Black-box Models

06/07/2021
by   Sahil Verma, et al.
7

Explainable machine learning (ML) has gained traction in recent years due to the increasing adoption of ML-based systems in many sectors. Counterfactual explanations (CFEs) provide “what if” feedback of the form “if an input datapoint were x' instead of x, then an ML-based system's output would be y' instead of y.” CFEs are attractive due to their actionable feedback, amenability to existing legal frameworks, and fidelity to the underlying ML model. Yet, current CFE approaches are single shot – that is, they assume x can change to x' in a single time period. We propose a novel stochastic-control-based approach that generates sequential CFEs, that is, CFEs that allow x to move stochastically and sequentially across intermediate states to a final state x'. Our approach is model agnostic and black box. Furthermore, calculation of CFEs is amortized such that once trained, it applies to multiple datapoints without the need for re-optimization. In addition to these primary characteristics, our approach admits optional desiderata such as adherence to the data manifold, respect for causal relations, and sparsity – identified by past research as desirable properties of CFEs. We evaluate our approach using three real-world datasets and show successful generation of sequential CFEs that respect other counterfactual desiderata.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/14/2021

Counterfactual Explanations for Machine Learning: Challenges Revisited

Counterfactual explanations (CFEs) are an emerging technique under the u...
research
01/18/2022

Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis

Being able to provide counterfactual interventions - sequences of action...
research
10/22/2021

ReLACE: Reinforcement Learning Agent for Counterfactual Explanations of Arbitrary Predictive Models

The demand for explainable machine learning (ML) models has been growing...
research
08/08/2022

Learning to Learn to Predict Performance Regressions in Production at Meta

Catching and attributing code change-induced performance regressions in ...
research
04/12/2021

Consequence-aware Sequential Counterfactual Generation

Counterfactuals have become a popular technique nowadays for interacting...
research
08/19/2023

Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: a Case Study on Hateful Memes

In the wake of the explosive growth of machine learning (ML) usage, part...
research
01/17/2022

Principled Diverse Counterfactuals in Multilinear Models

Machine learning (ML) applications have automated numerous real-life tas...

Please sign up or login with your details

Forgot password? Click here to reset