- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Existing Knowledge Graph Completion (KGC) methods rely on embedding similarity or graph connectivity, making it difficult to identify subgraphs truly influential for query-specific predictions. Furthermore, converting graphs into text for LLM input introduces substantial computational overhead. To address these limitations, RISE records triple-level embedding updates during KGE training and measures changes in prediction probabilities through rollback. It then identifies influential paths and constructs candidate-specific influential subgraphs. The selected subgraphs are encoded using a RelGNN and fused with KGE embeddings to form a Latent Structural Soft Prefix, which guides LLM-based candidate reranking. RISE outperforms existing methods on most evaluation metrics across four KGC benchmarks.
Critical strengths
- Well-Motivated Prediction-Aware Subgraph Selection
The paper identifies a limitation of conventional KGC subgraph selection methods: structural connectivity and heuristics may not adequately capture information useful for prediction. To address this, it proposes selecting query-specific influential subgraphs by tracking KGE optimization trajectories and measuring prediction probability changes under rollback. This prediction-sensitive approach is reasonable, as useful reasoning paths vary across queries and are difficult to define in advance. It enables the selection of predictive structural information without explicit path-level supervision.
- Comprehensive Experimental Evaluation
The paper evaluates its method on four datasets (Kinship-MH, UMLS, FB15K-237, and CoDEx-L), outperforming various KGC baselines on most metrics. Using the same Qwen3-8B backbone for applicable LLM-based baselines also improves comparison fairness. Figure 3 shows that rollback-guided selection outperforms structural plausibility and trajectory-magnitude-based selection, supporting the effectiveness of the proposed mechanism. Table 2 and additional analyses across KGE and LLM backbones further validate the main components. Overall, the experimental evaluation is comprehensive.
- Efficient Integration of Structural Information Through Latent Conditioning
Instead of converting selected subgraphs into natural language, the method encodes them into compact latent structural prefixes using a RelGNN and an adapter. Maintaining a fixed prefix tokens regardless of subgraph size reduces the overhead of lengthy text-based graph serialization while preserving structural information. The ablation results further support the effectiveness of this design.
Critical weaknesses
- Limited Methodological Novelty
A major concern is the substantial overlap between RISE and prior work. Gradient Rollback (Lawrence et al., 2021) already introduced rollback-based influence estimation, while GradPath (Di Mauro et al., 2024) and KGExplainer (Ma et al., 2025) explored prediction-aware path and subgraph selection. Similarly, incorporating KGE embeddings or query-specific subgraphs into LLMs through soft prefixes and graph encoders has been studied in KoPA (Zhang et al., 2024) and DrKGC (Xiao et al., 2025). Thus, RISE's primary contribution appears to be the integration of existing rollback-based influence estimation and subgraph encoding techniques into an LLM-based KGC framework, rather than a fundamentally new methodology.
- Downstream-Specific Optimization and Limited Generalizability
RISE selects influential subgraphs based on KGE prediction sensitivity for specific query–candidate pairs, followed by query-conditioned RelGNN encoding and LLM reranking. Consequently, the entire pipeline is closely tied to the downstream tail prediction objective. While task-specific optimization is reasonable, high prediction sensitivity does not necessarily imply general structural utility. Subgraph usefulness may depend on other criteria, such as structural sufficiency, path simplicity, or interpretability. The paper should clarify the scope and generalizability of its definition of influential subgraphs.
- Insufficient Justification of Selected Path Quality
The case study in Table 3 does not convincingly demonstrate that RISE selects better subgraphs than existing methods. For the query (Marco, husband of, ?), both DrKGC and RISE correctly predict Lucia, despite selecting 2-hop and 3-hop paths, respectively. It remains unclear what additional predictive value RISE's longer path provides. Although longer paths are not necessarily inferior, path quality should be evaluated based on their contribution to prediction rather than structural complexity alone. Similarly, the improvements observed with longer maximum exploration lengths in Figure 10 may result from increased candidate-path diversity rather than the inherent usefulness of longer paths.
- Methodological Complexity and Computational Overhead
RISE involves multiple components, including optimization trajectory tracing, path enumeration, dual-criterion preselection, rollback scoring, relational graph encoding, gated fusion, contrastive learning, and LLM reranking. Although ablation studies partially validate these components, the overall framework remains complex. In particular, trajectory map storage reaches 7.90 GB on FB15K-237 and 15.80 GB on CoDEx-L, while rollback-guided subgraph construction introduces additional offline computation. These computational and storage requirements raise concerns about the scalability and practical efficiency of the proposed approach.
Questions for authors
See Weakness.
7 comments
Detailed Responses to Reviewer 4qmC (1/3)
Detailed Responses
We thank the reviewer for the constructive feedback. We clarify RISE's methodological contributions and scope, and provide additional evidence on generalization, path quality, and computational efficiency below.
-W1. Clarifying Methodological Contributions
Our contribution lies in constructing rollback-guided influential subgraphs as candidate-specific structural evidence for LLM-based KGC, preserving candidate–evidence correspondence from selection to reranking. This is the motivation behind "Rollback-Guided Influential Subgraphs" in our title: determining which local structures support each candidate prediction and learning how to use those structures to distinguish competing candidates.
1) Efficient construction of influential subgraphs. GradPath evaluates both target-level influence and dependencies among path triples, requiring additional rollback-based probability evaluations. Our RISE controls path quality through structural/trajectory preselection, then evaluates only the target prediction's rollback sensitivity over a bounded path pool. This eliminates path-internal influence evaluations and limits expensive rollback scoring for each candidate, while retaining paths whose recorded updates support that candidate prediction. The resulting subgraphs provide prediction-relevant evidence for reranking at substantially lower construction cost: RISE achieves 5.3×/3.3× faster construction on UMLS/FB15K-237, while matching UMLS MRR and improving FB15K-237 MRR by 1.2 percentage points (Tab.1). Relative to Dual (without rollback), RISE also improves MRR by 4.0 and 3.0 percentage points on UMLS and FB15K-237, respectively, supporting rollback's additional value beyond structural/trajectory preselection.
Tab.1 Path-selector comparison
| Dataset | Method | MRR (%)↑ | Subgraph construction time (s/query)↓ |
|---|---|---|---|
| UMLS | RISE w/ GradPath | 90.9 | 4.42 |
| RISE w/ Dual (S_struct and S_trace only) | 86.9 | 0.75 | |
| RISE | 90.9 | 0.84 | |
| FB15K-237 | RISE w/ GradPath | 46.6 | 5.36 |
| RISE w/ Dual (S_struct and S_trace only) | 44.8 | 1.24 | |
| RISE | 47.8 | 1.64 |
2) From global embeddings or shared graphs to candidate-specific evidence. KoPA uses pretrained embedding prefixes, while DrKGC derives candidate embeddings from a shared, rule-guided query graph. RISE independently selects a query-sensitive subgraph for each candidate and fuses its query-conditioned representation with the candidate's global embedding. This helps the reranker distinguish competing candidates using local evidence relevant to the current query. Table 3 in the paper further supports our representation design: removing subgraph representations or query conditioning reduces performance on both datasets, indicating that local structural evidence and query-conditioned encoding both contribute to candidate reranking.
-W2. Clarifying Scope and Generalizability
1) Scope and selection criteria. We clarify that "influential" denotes model- and prediction-specific sensitivity. For a fixed KGE and its recorded updates, RISE preselects query-candidate paths using structural/trajectory scores, then prioritizes them by length-normalized rollback-induced reductions in candidate log-probability. Structural quality and path simplicity are incorporated into selection: S_struct favors plausible facts, while bounded path lengths/counts encourage compact evidence (Figures 9-10 in the paper). The case study (Table 5 in the paper) illustrates relational chains.
2) Downstream predictive value of influential subgraphs. We added Matched Path Replacement, replacing selected paths with alternatives of the same length and similar structural/trajectory scores, while preserving path count. Tab.2 shows that RISE outperforms this control on both datasets, supporting the selected evidence's predictive value beyond these controls.
Tab.2 Downstream value of selected paths
| Variant | UMLS (MRR / H@1) | FB15K-237 (MRR / H@1) |
|---|---|---|
| RISE w/ Dual (S_struct and S_trace only) | 86.9 / 84.9 | 44.8 / 38.7 |
| RISE w/ Matched Path Replacement | 89.6 / 87.1 | 46.7 / 40.1 |
| Our RISE | 90.9 / 89.1 | 47.8 / 41.5 |
The remainder of our response to W2, addressing generalization across KG conditions, is provided in the next comment.
Detailed Responses to Reviewer 4qmC (2/3)
3) Generalization across KG conditions. We further examine whether our RISE's predictive utility extends to noisy KGs, inductive KGs, evolving KGs and sparser KGs.
Under noisy KGs, we evaluated entity mislinking and relation mislabeling. Tab.3 shows that RISE consistently outperforms Dual, with its MRR advantage generally widening as noise increases. This advantage is consistent with candidate-specific prediction sensitivity: rollback evaluates how path-associated updates affect the candidate prediction, providing relevance information beyond structural plausibility and update magnitude to guide evidence selection under noise.
Tab.3 Robustness to noisy KGs
(a) Entity mislinking
| Dataset | Noise rate | Dual (MRR / H@1) | RISE (MRR / H@1) | RISE−Dual (MRR / H@1) |
|---|---|---|---|---|
| UMLS | 0% | 86.9 / 84.9 | 90.9 / 89.1 | +4.0 / +4.2 |
| 5% | 86.2 / 84.3 | 91.0 / 89.1 | +4.8 / +4.8 | |
| 10% | 85.4 / 83.1 | 90.1 / 88.2 | +4.7 / +5.1 | |
| 20% | 78.4 / 73.2 | 84.0 / 78.2 | +5.6 / +5.0 | |
| FB15K-237 | 0% | 44.8 / 38.7 | 47.8 / 41.5 | +3.0 / +2.8 |
| 5% | 41.6 / 35.2 | 45.1 / 38.2 | +3.5 / +3.0 | |
| 10% | 39.6 / 33.4 | 43.2 / 36.4 | +3.6 / +3.0 | |
| 20% | 36.8 / 30.7 | 40.4 / 33.5 | +3.6 / +2.8 |
(b) Relation mislabeling
| Dataset | Noise rate | Dual (MRR / H@1) | RISE (MRR / H@1) | RISE−Dual (MRR / H@1) |
|---|---|---|---|---|
| UMLS | 0% | 86.9 / 84.9 | 90.9 / 89.1 | +4.0 / +4.2 |
| 5% | 86.6 / 85.3 | 90.9 / 90.0 | +4.3 / +4.7 | |
| 10% | 83.9 / 82.3 | 90.5 / 88.5 | +6.6 / +6.2 | |
| 20% | 75.5 / 70.8 | 82.9 / 78.8 | +7.4 / +8.0 | |
| FB15K-237 | 0% | 44.8 / 38.7 | 47.8 / 41.5 | +3.0 / +2.8 |
| 5% | 38.2 / 30.1 | 41.9 / 32.5 | +3.7 / +2.4 | |
| 10% | 32.0 / 22.3 | 36.1 / 24.0 | +4.1 / +1.7 | |
| 20% | 19.0 / 8.2 | 23.5 / 9.0 | +4.5 / +0.8 |
For inductive KGs, five support facts per unseen entity enable embedding adaptation and provide recorded updates for rollback. Tab.4 shows that RISE achieves the highest MRR across all six settings. Its query-conditioned encoder reuses learned relational patterns to exploit multi-hop evidence connecting unseen entities to existing neighborhoods, complementing limited embedding adaptation.
Tab.4 Performance on inductive KGs (%)
| Dataset | #Unseen Entities | #Queries | DrKGC (MRR / H@1) | FtG (MRR / H@1) | SRP-KGC (MRR / H@1) | Ours (MRR / H@1) |
|---|---|---|---|---|---|---|
| UMLS | 10 | 152 | 47.3 / 34.9 | 30.7 / 24.3 | 53.1 / 48.7 | 64.3 / 57.9 |
| 20 | 227 | 42.1 / 30.4 | 28.4 / 21.6 | 49.8 / 45.4 | 57.4 / 51.1 | |
| 30 | 277 | 34.1 / 24.2 | 22.9 / 16.6 | 43.6 / 38.6 | 45.8 / 39.0 | |
| FB15K-237 | 100 | 454 | 31.3 / 22.5 | 28.9 / 21.8 | 37.6 / 34.8 | 38.3 / 33.9 |
| 200 | 799 | 26.1 / 18.1 | 24.2 / 15.8 | 30.7 / 27.8 | 33.6 / 27.0 | |
| 300 | 1665 | 20.4 / 13.9 | 22.1 / 14.7 | 25.3 / 22.6 | 28.4 / 23.8 |
For evolving KGs, we started with 90% of training facts and added the remainder in two equal batches, keeping validation/test sets fixed and recording new KGE updates for rollback. Tab.5 shows that RISE achieves the highest MRR and H@1 on both datasets in both rounds. Its advantage is consistent with candidate-specific use of updated evidence: recorded updates guide rollback-based path selection, while query-conditioned encoding integrates the selected structures into LLM reranking.
Tab.5 Performance under evolving KGs (%)
| Dataset | Update round | RotatE Recall@30 | DrKGC (MRR / H@1) | FtG (MRR / H@1) | SRP-KGC (MRR / H@1) | Ours (MRR / H@1) |
|---|---|---|---|---|---|---|
| UMLS | 1st | 97.0 | 79.8 / 74.4 | 58.2 / 49.8 | 44.1 / 36.8 | 90.5 / 88.5 |
| UMLS | 2nd | 97.1 | 81.6 / 73.7 | 58.0 / 50.5 | 45.1 / 37.8 | 90.8 / 88.7 |
| FB15K-237 | 1st | 68.5 | 42.8 / 33.7 | 41.6 / 33.5 | 45.0 / 37.2 | 48.1 / 41.3 |
| FB15K-237 | 2nd | 67.9 | 43.3 / 35.0 | 41.2 / 33.7 | 45.2 / 37.4 | 47.5 / 40.9 |
For sparser KGs, training-fact deletion (Figure 12) examines 0–30% removal on UMLS. RISE tolerates modest removal, consistent with its ability to select useful evidence from the remaining paths. Heavier deletion causes greater degradation, suggesting that fewer alternative connections limit the structural context available for reranking.
Summary of Paper Revision
Summary of Paper Revision
We have revised the paper to address reviewer 4qmC's concerns and questions as follows:
For W1, we have clarified two contributions: efficient rollback-guided selection, combining structural/trajectory preselection with bounded target-level scoring to avoid GradPath's path-internal influence evaluations; and candidate-specific structural learning, independently selecting and encoding query-conditioned subgraphs to preserve candidate–evidence correspondence through reranking, distinguishing RISE from KoPA's embedding prefixes and DrKGC's shared query graph. We have revised the contributions in Section 1 and the prior-work distinctions in Section 2, and have added the GradPath selector comparison and analysis to Figure 3.
For W2, we have clarified that "influential" denotes model- and prediction-specific sensitivity: rollback-induced reductions in candidate log-probability guide the selection of compact, structurally plausible evidence for reranking. The diagnostics in Table 4 of Section 4.4, with further analysis in Appendix F, have demonstrated additional predictive value when path count, length, and structural/trajectory scores are controlled. We have also expanded Appendix H to examine applicability to noisy, inductive, evolving, and sparser KGs.
For W3, we have clarified the case-study interpretation in Section 4.5, revised the Figure 9 discussion, and added "Path-Length Distributions and Rollback Selection" to Appendix H. We have explained that broader exploration expands the available evidence, while length-normalized rollback sensitivity determines path selection. The new statistics (Tables 19-20) have shown that two-hop paths remain dominant under default retention budgets, supporting selective use of a richer path pool rather than an inherent advantage of longer paths.
For W4, we have updated "Trajectory Storage and Loading Costs" and added "Component-Level Cost Analysis" to Appendix E. Across four datasets, lossless NPZ reduces storage by 87.7–88.0% and provides 8.42–13.43× loading speedups. UMLS profiling shows under 0.20 s/query and 138 MB working set per non-LLM component. We have also updated the performance-latency comparison, showing that RISE achieves the highest MRR (47.8%) with competitive online latency (2.21 s/query) on FB15K-237.
In addition, because we have evaluated broader generalization settings and substantially reduced trajectory-storage costs through lossless NPZ storage, we have updated the limitations in Section 5 "Conclusion" accordingly.