Role Support in Knowledge-Graph Error Ranking: Predictor Regimes and Evaluation Policies
Not on the map. Why?
Abstract (arXiv)
When do role-specific training counts improve knowledge-graph error ranking? We evaluate fifteen from-scratch predictors, nine development-selected continuation stages, and six fixed ensembles across three static graphs. A positive penalty for missing training support has no stable error-ranking orientation: stronger ComplEx training reverses its pooled error AUROC from 0.689 to 0.364 on FB15k-237, and from 0.729 to 0.430 in a prospectively specified CoDEx-S check. Pair decomposition shows that reversal also survives pair-weighted within-relation evaluation, but not equal-relation averaging. The statement depends on which relations and query pairs receive weight. Learned continuous counts remain useful: they improve AURC and Brier beyond explicit ensemble disagreement in twelve original ensemble/head comparisons and satisfy all four predefined external-dataset AURC contrasts. Binary indicators add no information beyond their defining counts and have less stable fitting effects. Candidate, target, population and acceptance policies change the comparisons; fixed development thresholds do not preserve a common test answer rate. The external study was fixed before inspection of its test outcomes, whereas subsequent explanations and reused-graph controls are explicitly exploratory. These measurements support relation-aware count baselines and policy-specific support diagnostics, not a new uncertainty decomposition, causal training mechanism, calibrated factual truth, or graph-population guarantee. Saved checkpoints, ledgers and separately authored numerical implementation replays make the scoped findings inspectable.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 26 Dec 2025.
Builds on
15 of 21 references.
References · 15
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,902
- 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 930
- 2016Complex Embeddings for Simple Link Predictioncited by 899
- 2017Deep Bayesian Active Learning with Image Datacited by 816
- 2017Convolutional 2D Knowledge Graph Embeddingscited by 729
- 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
- 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
- 2015Type-Constrained Representation Learning in Knowledge Graphscited by 34
- 2021Probabilistic Entity Representation Model for Reasoning over Knowledge Graphscited by 28
- 2018Embedding Uncertain Knowledge Graphscited by 25
- 2021Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoningcited by 22
- 2023Toward Degree Bias in Embedding-Based Knowledge Graph Completioncited by 17
Built on by
Citing papers per year: 2026: 1.
1 paper.