- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper studies the trade-off between counterfactual fairness and predictive accuracy. The main idea is that enforcing exact counterfactual fairness can reduce predictive performance, especially when the sensitive attribute, or some of its causal descendants, contains useful information for the prediction. To address this, the authors propose a relaxed version of counterfactual fairness controlled by a parameter (), which determines how much of the counterfactual prediction gap of the Bayes-optimal predictor is allowed to remain. The paper first formulates the problem as a constrained optimization problem and derives the optimal predictors for regression under squared loss and for binary classification under cross-entropy loss. In the regression case, they obtain an explicit solution that can be seen as an interpolation between the fully counterfactually fair predictor and the unconstrained Bayes-optimal predictor. They also derive the corresponding excess risk analytically. For cross-entropy loss, the optimal predictor does not have the same closed-form expression and is instead characterized through a nonlinear equation. The authors then consider the more realistic case where neither the Bayes-optimal predictor nor the counterfactual generator is known and both need to be estimated from data. They derive upper bounds showing how estimation errors affect the predictive excess risk. Finally, the theoretical results are validated using synthetic experiments, while semi-synthetic experiments on the Law School and Adult Income datasets compare the proposed approach with other methods.
Critical strengths
In my opinion, here are the strong aspects of the paper:
-
The paper addresses an important concern related to the use of causality in AI fairness, namely its practical applicability. Exact counterfactual fairness can come at the cost of predictive accuracy, while the underlying causal mechanisms are generally not known in practice. Studying relaxed fairness guarantees under imperfect causal knowledge is therefore a relevant research direction.
-
The proposed parameter () is also easy to interpret, as it controls the fraction of the original counterfactual prediction gap that is allowed to remain. This provides a clear connection between exact counterfactual fairness and unconstrained prediction.
-
The authors characterize the optimal fairness-constrained predictors for both squared loss and cross-entropy loss. In particular, the explicit interpolation result and the excess-risk expression obtained for squared loss are interesting and provide a clear interpretation of the fairness-accuracy trade-off.
-
The extension to the case where the Bayes-optimal predictor and the counterfactual generator need to be estimated is also valuable. The derived excess-risk bounds help understand how estimation errors and imperfect causal knowledge affect predictive performance. The synthetic and semi-synthetic experiments provide initial empirical support for these theoretical results.
Critical weaknesses
The paper is unnecessarily difficult to follow, and understanding the objectives of the different sections requires considerable effort. The technical introduction introduces several mathematical quantities before clearly establishing the overall framework and motivation. The objectives of Sections 3–6, as well as the connections between them, should be explained more explicitly. Several editorial issues also affect readability. Equations are not numbered, some variables, such as (q), are insufficiently defined, and the notation is not always introduced in a systematic way. A high-level overview of the methodology at the beginning of the paper would considerably improve the presentation.
The counterfactual generator () should also be more explicitly connected to Pearl's abduction–action–prediction procedure. This would help clarify the role of the latent state and the invertibility assumption. The invertibility assumption is particularly strong, and its practical implications deserve further discussion. Moreover, invertibility alone does not guarantee that the true counterfactual mechanism can be identified from observational data, which is an important limitation in practice.
Section 5 derives upper bounds on the predictive excess risk resulting from errors in the estimated Bayes predictor and counterfactual generator. However, the paper does not explicitly characterize how these estimation errors affect the actual fairness level of the resulting predictor. The fairness constraint is defined with respect to the true counterfactual prediction gap, while the practical construction relies on estimated quantities. An analysis of the discrepancy between the intended fairness constraint and the fairness actually achieved under estimation errors would strengthen the practical contribution.
The experimental evaluation could also be stronger. The synthetic experiments mainly confirm the qualitative theoretical behavior under a relatively simple causal model. It would be useful to directly evaluate how tight the proposed excess-risk bounds are in practice. The semi-synthetic experiments are limited to two datasets and a relatively small set of baselines. In addition, the proposed method largely overlaps with L2 regularization on the Law School dataset, while the improvements on Adult Income are not consistent across all settings. A broader evaluation, including more diverse datasets, stronger baselines, and uncertainty estimates, would provide stronger empirical support for the claimed benefits of the method.
Questions for authors
Q1. In the practical setting, the fairness-constrained predictor is constructed using an estimated Bayes predictor (\hat\mu) and an estimated counterfactual generator (). Can the authors derive a theoretical bound on the deviation between the achieved counterfactual gap and the prescribed relaxation level, for example, Such a result would complement the excess-risk analysis and provide a stronger guarantee concerning the practical control of counterfactual fairness.
Q2. Section 5 derives excess-risk bounds involving errors in the counterfactual generator and Bayes predictor. Can the authors evaluate the tightness of these bounds experimentally, rather than only validating their qualitative behavior? In particular, how informative are the bounds when both components are estimated simultaneously, and how does the prescribed relaxation parameter (\epsilon) relate to the achieved RTE under increasing estimation errors?
3 comments
Weakness and Question 2 — Bound tightness and achieved RTE
Thank the reviewer for suggesting the quantitative evaluation. We conduct complementary experiments examining how closely the excess-risk bounds can be approached and how the prescribed relaxation level relates to achieved RTE. Given the rebuttal space limit, the tables below present selected results from the broader set of experiments across error budgets and relaxation levels.
To assess worst-case tightness, we constructed simultaneous perturbations of the counterfactual generator and Bayes predictor within error budgets and , respectively, seeking configurations that approach the upper bounds. We report the largest attained excess risk as a percentage of the theoretical bound.
For regression, the bound is attained exactly (100% tightness), consistent with its proof, where equality conditions can hold simultaneously. For classification, a selected setting in Table 1 achieves 98.43%–99.77% tightness across . These results demonstrate that the bounds can be attained or closely approached under simultaneous errors in both components. The remaining gap is consistent with the its proof derivation, which combines several intermediate upper bounds whose equality conditions need not hold simultaneously.
Table 1.
| Tightness (%) | |
|---|---|
| 0.0 | 98.4305 |
| 0.1 | 98.5617 |
| 0.2 | 98.6935 |
| 0.3 | 98.8261 |
| 0.4 | 98.9593 |
| 0.5 | 99.0932 |
| 0.6 | 99.2277 |
| 0.7 | 99.3630 |
| 0.8 | 99.4989 |
| 0.9 | 99.6356 |
| 1.0 | 99.7733 |
For achieved RTE, we retain the original DGP and estimation settings. For brevity, Tables 2–3 present regression results at and , the two endpoints of our original training sample size. The tables report mean (SD) over 30 repetitions, evaluated with different generator error and sample size .
With true , achieved RTE equals the prescribed , despite estimation error in . With misspecified , RTE initially decreases as decreases from 1, but turns upward at small . This reflects stronger enforcement using inaccurate counterfactuals, which can overcorrect the prediction difference between true counterfactual pairs. Smaller generator errors improve overall agreement with the prescribed level, while larger training samples generally reduce variability.
Table 2. Regression RTE, .
| True | |||
|---|---|---|---|
| 0.0 | 0.0000 (0.0000) | 0.4136 (0.0205) | 0.7964 (0.0412) |
| 0.1 | 0.1000 (0.0000) | 0.2825 (0.0155) | 0.6271 (0.0339) |
| 0.2 | 0.2000 (0.0000) | 0.1560 (0.0110) | 0.4577 (0.0271) |
| 0.3 | 0.3000 (0.0000) | 0.1746 (0.0172) | 0.2953 (0.0193) |
| 0.4 | 0.4000 (0.0000) | 0.2604 (0.0188) | 0.2796 (0.0240) |
| 0.5 | 0.5000 (0.0000) | 0.3683 (0.0172) | 0.3409 (0.0267) |
| 0.6 | 0.6000 (0.0000) | 0.4878 (0.0143) | 0.4393 (0.0261) |
| 0.7 | 0.7000 (0.0000) | 0.6124 (0.0109) | 0.5606 (0.0218) |
| 0.8 | 0.8000 (0.0000) | 0.7401 (0.0073) | 0.6986 (0.0155) |
| 0.9 | 0.9000 (0.0000) | 0.8695 (0.0037) | 0.8463 (0.0080) |
| 1.0 | 1.0000 (0.0000) | 1.0000 (0.0000) | 1.0000 (0.0000) |
Table 3. Regression RTE, .
| True | |||
|---|---|---|---|
| 0.0 | 0.0000 (0.0000) | 0.4039 (0.0092) | 0.7808 (0.0180) |
| 0.1 | 0.1000 (0.0000) | 0.2771 (0.0063) | 0.6163 (0.0144) |
| 0.2 | 0.2000 (0.0000) | 0.1553 (0.0075) | 0.4518 (0.0110) |
| 0.3 | 0.3000 (0.0000) | 0.1731 (0.0112) | 0.2980 (0.0149) |
| 0.4 | 0.4000 (0.0000) | 0.2606 (0.0065) | 0.2826 (0.0225) |
| 0.5 | 0.5000 (0.0000) | 0.3703 (0.0043) | 0.3425 (0.0163) |
| 0.6 | 0.6000 (0.0000) | 0.4900 (0.0033) | 0.4428 (0.0101) |
| 0.7 | 0.7000 (0.0000) | 0.6147 (0.0026) | 0.5646 (0.0060) |
| 0.8 | 0.8000 (0.0000) | 0.7417 (0.0019) | 0.7020 (0.0038) |
| 0.9 | 0.9000 (0.0000) | 0.8703 (0.0009) | 0.8482 (0.0021) |
| 1.0 | 1.0000 (0.0000) | 1.0000 (0.0000) | 1.0000 (0.0000) |
I appreciate the effort made to address my concerns, particularly the new bounds on achieved counterfactual fairness and the experiments evaluating the tightness of the excess-risk bounds. These additions strengthen the paper and provide useful clarification. However, while the rebuttal addresses several of my technical questions, I do not consider the additional evidence sufficient to justify a change in my overall assessment.
Thanks the reviewer for the detailed feedback and we address the concerns below.
Weakness — Presentation
We will improve the presentation by adding a brief roadmap clarifying the connections between Sections: Section 2 introduces the problem setup, Section 3 characterizes the oracle optimal predictors, Section 4 presents the practical estimation procedure, Section 5 establishes the excess-risk bounds, and Section 6 provides empirical evaluations. We will also clarify the notation and number key equations.
Weakness — Counterfactual generator and invertibility
We thank the reviewer for the suggestion. We will make the connection between G⋆ and Pearl's abduction–action–prediction procedure more explicit. Specifically, given (x,a), invertibility allows us to recover the latent state u (abduction). We then intervene on A while keeping u fixed (action), and obtain the counterfactual G⋆(x,a,1−a)=x1−a(u) (prediction).
The adoptation of invertibility assumption is mainly to firstly establish the fundamental theory in a relatively simplified setting, without simultaneously dealing with the additional uncertainty arising from non-unique counterfactuals. In fact, even under this simplified setting, characterizing the optimal predictors and deriving the risk analysis already involve nontrivial theoretical challenges. While the theoretical results are established under invertibility, Section 6 deliberately considers experiments based on real data without imposing this assumption.
Regarding identification. The invertibility only ensures the uniqueness, which is distinct from identifying the counterfactual mechanism from observational data. We will clarify this distinction explicitly.
Weakness and Question 1 — Deviation from the prescribed fairness level
Based on the assumptions in section 5, we have:
For regression:
\leq(1-\epsilon)L\eta_G+2\eta_\phi.$$ For classification: $$|\Delta_{\hat\phi^\epsilon}(u)-\epsilon\delta(u)| \leq 2C_\rho(1-\epsilon)(L\eta_G+2\eta_\phi) +2\epsilon\eta_\phi.$$ We will include these results and their proofs in the revised manuscript to provide a more complete theoretical characterization of the achieved counterfactual fairness guarantees.