- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a unified framework for improving accuracy, coverage efficiency, and fairness in knowledge graph embedding (KGE) through dual clustering of entities and relations. It learns low-rank representations of entity and relation embeddings, clusters these representations, and uses the resulting clusters for both cluster-aware self-adversarial KGE training to improve link-prediction accuracy and cluster-wise conformal calibration to maintain coverage and improve prediction set size and prediction-set-size disparity (fairness). The empirical results show that the proposed method outperforms existing KGE methods and KGE + CP methods on all of these metrics. The paper also presents a disparity decomposition to give a bound on the overall unfairness, which is attributed to prior work.
Critical strengths
-
The paper studies an important problem of improving uncertainty quantification and fairness in KGE, in addition to link-predictive accuracy. Addressing all three objectives within a unified framework is interesting, particularly because conformal prediction for KGE is typically applied as a post-hoc mechanism rather than being integrated with representation learning.
-
The dual clustering approach, which explicitly considers entity-relation heterogeneity, is an intuitive and natural architectural choice for knowledge graphs. Further integrating the resulting clusters for both KGE training and conformal calibration is also interesting.
-
The paper has a reasonably comprehensive experimental evaluation across multiple existing (conformal) KGE methods and benchmark datasets, with consistent improvements in predictive accuracy, average prediction-set size, and the proposed prediction-set-size disparity metric against the considered baselines.
Critical weaknesses
-
The theoretical contribution and novelty surrounding Theorem 4.1 seem to be quite overstated. The theorem statement and proof match closely with Theorem 4.1 in [1], which the authors do cite, but already establishes essentially the same prediction-set-size disparity decomposition. Further, the theorem applies to any general label clustering function, so it's not clear what the low-rank dual-clustering procedure adds to the bounds of theory.
-
For the fairness results, the authors define groups based on query difficulty following Zhu et al. (2025). (Note the citation is incorrect in the paper and cites the subsequent 2026 work.) While the metric is useful in assessing robustness to different query difficulties, it would be nice to see results that consist of sensitive attributes that may result in actual bias (e.g., race or gender component). The YAGO3-10 dataset the paper already evaluates includes such attributes (e.g., gender) that could be useful for fairness evaluation.
-
There is limited novelty in the cluster-wise conformal prediction component, as it closely resembles the filtering framework in [2]. In [2], you define a filtering function that partitions or selects calibration examples from the full calibration set and provides conditional guarantees. Admittedly, the specific objectives do differ, since [2] filters based on group fairness metrics and this paper uses learned clusters.
-
The proposed framework contains several interacting components, including low-rank representation learning, entity/relation clustering, cluster-aware self-adversarial training, and cluster-wise conformal calibration, but the empirical evaluation does not include an appropriate ablation study.
[1] Liu et al., 2026. Beyond Procedure: Substantive Fairness in Conformal Prediction, ICML 2026
[2] Vadlamani et al., 2025, A Generic Framework for Conformal Fairness, ICLR 2025
Questions for authors
(See weaknesses)
How much does each component of the framework contribute to the overall performance?
Do the coverage guarantees hold empirically within individual clusters/groups?
4 comments
I would like to thank the authors for their detailed response and additional experiments. The new experiments address most of my concerns and strengthen the paper. A few of my concerns remain.
-
[W1] While the authors do attribute Theorem 4.1 to Liu et al. (2026), my concern is that the theoretical analysis does not appear to provide additional insights beyond those already established in that work. In particular, the original theorem already applies to arbitrary clustering functions, and the authors do not theoretically establish that their proposed low-rank dual clustering provably reduces the terms in Eq. 19. Can the authors clarify the theoretical insights from their framework, or dial back on any claims of theoretical novelty?
-
[W2] I appreciate the gender-based evaluation, but can you clarify what you mean by "Individual group EC"? Do all of the gender groups achieve the empirical coverage? If so, making this clearer or explicitly listing each group and its metrics would make this table much stronger.
-
[W4] The ablation results look quite interesting. One additional experiment that could be useful is an entity-only vs. relation-only clustering comparison to establish the importance of dual clustering.
Overall, the rebuttal addresses most of my empirical concerns and strengthens the paper. While some concerns remain, and I would appreciate further clarification from the authors, I believe these can be addressed relatively easily. Thus, I will increase my score.
We thank again for the time and careful effort you put into our work and provide the insightful comments. We truly appreciate your positive feedback on our rebuttal and increase your score. We will for sure response to the remained issues when we get the experimental results.
We thank you again for giving us opportunities to make more clarification.
W1: Novelty
Prior theories (Liu 2026) are only proved for and applicable to classification tasks. We prove the theories for the KGE ranking task. And then, we propose dual clustering to training process which further controls intra-cluster heterogeneity (embeddings within the same cluster) and cross-cluster spread (embeddings from different clusters) by adaptively adjusting the entity embeddings and relation embeddings while learning clusters end-to-end.
W2: Individual group EC
Individual group EC refers to that the results for each of the gender groups. We report results for each group.
| YAGO3-10 | EC (male) | EC ( female) | EC (unknown) | APSS | (gender groups) |
|---|---|---|---|---|---|
| CondKGCP | 0.90 | 0.90 | 0.90 | 5698 | 3209 |
| Mondrian CP | 0.91 | 0.90 | 0.90 | 5763 | 3004 |
| Ours | 0.91 | 0.90 | 0.90 | 4641 | 2957 |
W4: Ablation
We report ablation compared to (i) entity-only clustering; (ii) relation-only clustering:
| WN18RR | EC | APSS | |
|---|---|---|---|
| CondKGCP | 0.90 | 5463 | 8506 |
| Mondrian CP | 0.90 | 4982 | 8130 |
| (i) | 0.91 | 3844 | 7531 |
| (ii) | 0.90 | 4485 | 7590 |
| Ours | 0.91 | 3517 | 7165 |
We can see that dual clustering is helpful in APSS and , and entity clustering is more helpful in APSS.
We thank the reviewer 5PXo for recognizing the value of taking dual heterogeneity into jointly addressing accuracy, coverage, and fairness, and for highlighting our results and experiments. We also thank the reviewer giving us opportunities to response to novelty and contribution, fairness evaluation, ablation, and individual group coverage guarantee. We will revise our paper accordingly.
W1, W3: Theoretical and methodology novelty and contribution
The current theorem applies to an arbitrary clustering. It explains how within-cluster heterogeneity enters the set-size-disparity bound. Thus, any clustering-based CP can reduces max set-size parity. As explained in our paper lines 314-356, we propose dual heterogeneity modeling and clustering to reduce the first two terms in Eq. (19). And existing conditional/clustered conformal prediction did not influence training process while our method uses factorization-based clustering and new cluster-aware self-adversarial losses which consider entity and relation heterogeneities. Empirical results also show that we actually achieve smallest Δ with smallest APSS and without violating coverage. Meanwhile, a coarse clustering will result in less calibration samples in each cluster. And less calibration samples in each cluster will result in larger average prediction set size.
Existing conditional/clustered conformal predictions and fairness notions based on conformal set sizes or group-conditional coverage [1, 2] do not influence any training process to improve accuracy and only run the post-hoc CP with known clusters or sensitive classes. These methods all need known sensitive features or labels. We propose negative sampling and contrastive learning with factorization-based clustering and weighting that models dual entity and relation heterogeneity in embeddings to further improve accuracy, coverage, and fairness. We propose the first unified KGE framework and conduct evaluation to jointly addresses accuracy, coverage, and fairness.
W2, Q2: Fairness evaluation and individual group coverage guarantee
Existing KGE benchmark datasets usually have no known sensitive features or labels, and thus we follow reference (Liu 2026) in our paper: reduced max set-size parity is more reasonable for fairness in scenarios that require coverage guarantee but have no sensitive features or labels. We note that Δ alone is insufficient: equal and large set sizes give Δ=0 but this is without utility. Thus, in the paper, We evaluate Δ jointly with empirical coverage and average prediction set size. Fairness improvements are only claimed on lower Δ without violating coverage or inflating APSS. We use Δ as a diagnostic of fairness only after we meet the coverage target and achieve smallest APSS.
We report experiments compared to Mondrian CP. During the Mondrian CP calibration, the difficulty groups were constructed after training KGE models and based on the model ranks of the true answers using the validation dataset.
We can see that our method meet the coverage target, achieve smallest APSS and better fairness than Mondrian CP.
Some person entities from the YAGO3-10 dataset has gender attributes, but the rest person entities are still unknown. We further report experiments directly based on such sensitive gender groups, instead of difficulty groups.
We can see that our method still achieve the empirical coverage, smallest APSS and better fairness than Mondrian CP. And our method hold the coverage guarantees empirically within individual gender group.
W4, Q1: Ablation
We report ablation compared to (i) clustering raw embeddings; (ii) training without cluster-aware adversarial weighting; (iii) without cluster-wise CP; (iv) training without low-rank and cluster-aware adversarial weighting; and Mondrian CP baseline:
We can see that each component is helpful in APSS and Δ.