- Rating
- 2
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes DICTUM, a counterfactual generation method for mixed-type tabular data. It first employs a -DPP to select opposite-class targets that balance proximity and diversity, and then trains a conditional diffusion model incorporating branching sampling, constraint projection, and -DPP post-processing to generate counterfactual sets.
Critical strengths
- The motivation is reasonably sound. The method considers a broader range of alternatives than relying solely on nearest-neighbor training targets.
- The results are generally good, with favorable performance in continuous-feature proximity, LOF, and diversity across five datasets.
Critical weaknesses
-
Lack of novelty. The mixed-type diffusion backbone and per-column noise schedules are largely inherited from TabDiff, the branching guidance draws on SVDD, and DPP is an existing set-selection tool. The contribution appears primarily to be a combination of these existing methods.
-
DiCE already uses DPP to encourage diversity in counterfactual sets, DiCoFlex already supports diverse counterfactual generation and inference-time constraint adjustment. Therefore, I think, “generating diverse counterfactuals and adapting to user requirements at inference time” does not, on its own, constitute a major innovation. If my understanding is correct, the baselines randomly select valid candidates, whereas DICTUM uses k-DPP post-processing. The same post-processing should be applied to all methods before comparing the generative models.
-
The coverage and comparison of recent related work are insufficient. For example, both [1] and [2] have studied counterfactual explanations for tabular data, and [2] specifically investigates diffusion-based counterfactual generation for mixed-type tabular data.
-
Algorithm 1 explicitly filters out candidates whose predictions do not match the target class or that violate constraints before applying k-DPP. Therefore, a final validity close to 1 does not directly demonstrate a high success rate for the original generation process.
[1] Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity [2] Tabular Diffusion Counterfactual Explanations
Questions for authors
See Weaknesses.
3 comments
Thank you for the rebuttal, the additional experiments are meaningful, so I am wllling to raise my score.
Dear Reviewer, Thank you very much for your positive feedback and for acknowledging our additional experiments. We are extremely glad to hear that they successfully addressed your concerns. We noticed that the score in the system has not been updated yet. We would be very grateful if you could kindly reflect your mentioned score increase in the system whenever you have a moment.
Response to Reviewer cnxs
We thank the reviewer for the feedback.
W1 + W2.1. Novelty
DICTUM is not a backbone swap. Its core idea is to decouple learning a broad counterfactual distribution p(x′|x,y′) from imposing user preferences on it at inference. This needs two things DiCoFlex lacks: training targets covering several recourse strategies, not one neighbourhood (k-DPP vs. kNN), and a sampler with intermediate states, so any black-box constraint can steer generation step by step (the branching noted in S2). A flow maps noise to a sample in one pass: it can only filter finished samples, and its control is limited to constraint types seen in training (no monotonicity). The ablations support combining the two: with our k-DPP selection given to DiCoFlex (response to 5tWg), DICTUM’s generator alone still yields lower LOF and higher diversity, and step-wise branching meets a feature-change budget that post-hoc filtering cannot enforce.
W2.2. Same post-processing for all methods
The k-DPP selection is part of DICTUM by design, not an add-on. DICTUM is trained on k-DPP-curated targets, so it learns a distribution over diverse valid counterfactuals, and the post-hoc selection is the inference counterpart of the same Gower-based kernel. Each baseline is evaluated with the selection of its original paper: DiCE optimises diversity within its own objective.
We applied our k-DPP post-processing to DiCoFlex and removed it from DICTUM (response to 5tWg). Even without k-DPP, DICTUM has the best LOF on all five datasets and higher diversity than every baseline except DiCE on Default and GMC, whose proximity is 3–6× worse (Table R1). The gap therefore comes mainly from the generator, not the selection.
Table R1.
W3. Related work
We thank the reviewer for the references and have added both to §2. [2] (TDCE) guides an unconditional tabular diffusion model with gradients of a differentiable classifier, using a Gumbel-softmax relaxation for categorical features, and produces one counterfactual per query. DICTUM instead learns p(x′∣x,y′) from diverse targets, needs only the classifier's predictions, and returns a diverse set per query under immutable and monotone constraints. [1] (DensityFlow) trains a density-guided Neural ODE so that single counterfactuals stay valid under model multiplicity, which is complementary to our goal.
W4. Validity and filtering
The "Validity" column measures the returned set, not the sampler. It is the fraction of the k=10 returned counterfactuals classified as y′, computed after the P=100 candidates per query have been filtered. The filter gives DICTUM no advantage and we claim none. A query whose pool contains no valid candidate is not discarded. It receives invalid candidates, and these count as failures. A value of 1.00 therefore means that, up to rounding, each of the Q=2000 queries had at least k=10 valid candidates among its 100.
We report pool validity separately: the fraction of the P=100 raw candidates classified as y′ before any filtering, for every method and dataset.
Table R2. Pool validity before filtering (P=100, Q=2000).
DiCE and CCHVAE optimise each candidate per query until it is valid, so their pools are nearly all valid at a higher cost. DICTUM samples without per-query optimisation; still, every query has a valid candidate and all have at least k=10, which is why the returned sets reach 1.00.