FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching

Key points

• In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome.1
• To be useful in practice, such an explanation should change few features and change them as little as possible, properties known as sparsity and proximity.1
• We solve this transport with flow matching, which we extend to mixed feature types with a novel mixed flow operator, and exploit the resulting geometry to optimise for sparsity through a gating network that minimises the number of features the transport changes.1
• Extensive experiments on six benchmark datasets demonstrate that FlowCF produces the best numerical sparsity and proximity, changing 29% of the numerical features where the best baseline changes 89%, at 70% smaller displacement, while remaining comparable on the other desiderata.1

Sources (1)

• [1]FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 03:27 PM

  In this paper, we propose FlowCF, a model-agnostic generative method that frames CF generation as sparse transport from the factual to the target class.

  In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome.

Extractive summary: sentences quoted from the sources.