CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations

TL;DR

CounterFlowNet is a novel generative method that produces high-quality, diverse counterfactual explanations for models, effectively handling heterogeneous features and user constraints through sequential feature modifications.

Contribution

It introduces a sequential, GFlowNet-based approach for generating counterfactual explanations that satisfy multiple desiderata and constraints without retraining.

Findings

Achieves superior validity, sparsity, and plausibility trade-offs.

Supports continuous and categorical features seamlessly.

Enforces actionability constraints at inference time.

Abstract

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple high-quality explanations that (1) affect only a small portion of the features, (2) can be applied to tabular data with heterogeneous features, and (3) are consistent with the user-defined constraints. We propose CounterFlowNet, a generative approach that formulates CF generation as sequential feature modification using conditional Generative Flow Networks (GFlowNet). CounterFlowNet is trained to sample CFs proportionally to a user-specified reward function that can encode key CF desiderata: validity, sparsity, proximity and plausibility, encouraging high-quality explanations. The sequential formulation yields highly sparse edits, while a unified action space seamlessly supports continuous and categorical features. Moreover, actionability constraints, such as immutability and monotonicity of features, can be enforced at inference time via action masking, without retraining. Experiments on eight datasets under two evaluation protocols demonstrate that CounterFlowNet achieves superior trade-offs between validity, sparsity, plausibility, and diversity with full satisfaction of the given constraints.