- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes a framework for auditing downstream model fairness without requiring access to the trained model or its predictions. It introduces stage-local Shapley certificates based on information-theoretic dependence measures and establishes one-sided guarantees bounding sensitive-attribute leakage and downstream fairness violations. The authors evaluate 26 measures across seven datasets and multiple downstream predictors, examining attribution fidelity, computational efficiency, and robustness to model choice. Additional experiments investigate scalable Shapley approximation and the effects of biased upstream supervision on fairness auditing.
Critical strengths
- The paper addresses an important and practical limitation of fairness auditing, where auditors may not have access to downstream models. The formalization of information-access constraints and the one-sided theoretical guarantees provide a useful foundation for model-independent auditing.
- The empirical evaluation is extensive, covering multiple dependence measures, datasets, and downstream predictors. The computational cost analysis and experiments on inherited supervision provide valuable insights into the limitations and practical applicability of the proposed certificates.
Critical weaknesses
- The theoretical novelty is somewhat limited, as the main fairness guarantees follow from established information-theoretic inequalities. Furthermore, these guarantees are one-sided and apply to specific MI/CMI measures rather than all evaluated certificates, limiting their ability to predict actual downstream fairness violations.
- The attribution evaluation relies on leave-one-out feature effects rather than ground-truth Shapley attributions, making it difficult to fully establish attribution fidelity. Additionally, most experiments use low-dimensional tabular datasets, the main benchmark averages only three seeds, and the applicability to high-dimensional learned representations remains unclear.
- The multi-stage evaluation is relatively limited, relying on a controlled upstream label-bias mechanism. While the experiments demonstrate sensitivity to inherited supervision, the certificates cannot reliably determine the direction of downstream fairness harm when true labels are unavailable.
Questions for authors
- Can the authors quantify how tight or informative the proposed MI/CMI fairness bounds are for the actual downstream predictors, rather than primarily evaluating attribution agreement?
- Can the authors evaluate attribution fidelity against model-based Shapley references instead of relying only on leave-one-out feature effects?
- How well would the framework scale to high-dimensional learned representations or more complex multi-stage pipelines, where exact Shapley computation becomes infeasible?
- How should auditors interpret certificates computed from potentially biased inherited supervision when reliable reference labels are unavailable?
2 comments
Rebuttal reminder; PDF uploaded (all 4 points addressed)
Dear Reviewer TZdx,
With the discussion closing on Nov 18 (AoE), we would kindly ask you to check whether our responses address your concerns.
The 4 points of our summary (from our rebuttal above) are in the revised PDF:
- W1 + Q1 (Tightness). The bound is reported next to the realized gap on all 7 datasets (new Sec5.3, Tbl3 + Tbl17; table in our most recent reply to 7enP): the TV cap is within 1.1-1.4x of the realized gap on COMPAS, 1.1-1.3x on ACS Emp. and 1.8-1.9x on ACS Income, and loose elsewhere
- W2 + Q2 (SV Ref + seeds). The SV Ref is the main one in Sec5.3 + AppJ, now on all 7 datasets (Tbl17), with 5 seeds throughout
- W2 + Q3 (Dimension + learned representations). Sec5.5 + Discussion/Limitations
- W3 + Q4 (Inherited labels). Sec5.6 + Limitations, with how to read certificates without reference labels
Corrections to our rebuttal above; random signed 33-37%, not 33-36%; speedup over 60x, not >72x
If any part remains unclear, we would be glad to clarify it right away.
Official Rebuttal to Reviewer TZdx
We thank the reviewer for their time and detailed feedback and for finding our work valuable. We respond below.
New numbers use the paper's pipeline on Adult + COMPAS (7predictors x 5seeds); our revision will extend them to all 7 datasets
W1 + Q1 (Novelty, One-sided guarantee + Tightness): We agree with the reviewer's assessment and clarify 3 points:
W2 + Q2 (LOO Ref vs Shapley Ref + Seeds): Done; answering to the concern of "model-based Shapley references":
W2 + Q3 (Dimension + Learned representations):
W3 + Q4 (Multi-stage study + Biased inherited labels): We see Sec5.5 as a first controlled study of this question; we state its limits clearly as follows:
Summary. (1) The guarantee is a standard inequality used as a set-level certificate; we now also measure its tightness. (2) SV Ref is adopted; same conclusions hold. (3) The 20-feature limit matches actionable audits. (4) On inherited labels, the limit + how to read the certificate are stated. We hope these clarifications address the soundness concerns and the reviewer will consider raising the score.