Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Recipe-Controlled Decoder Audit for Structural Knowledge-Graph Completion

About

We present a recipe-controlled decoder audit (RCDA) for structural transductive knowledge-graph completion (KGC). The audit asks a simple reporting question: before attributing gains to an encoder or training recipe, what changes when the decoder is swapped under the same recipe? Using ComplEx and DistMult as the primary controlled pair, with targeted RotatE/TransE spot-checks, we evaluate seven benchmarks. On five standard KGs, ComplEx-vs-DistMult differences are modest but consistent under our recipe (+0.005 to +0.012 MRR), whereas CompGCN-style encoder effects vary more by dataset. On small KGs, decoder effects become the main diagnostic: Kinship shows a stable ComplEx advantage of +0.143 MRR (6 seeds), while UMLS favours ComplEx by +0.022 MRR in a clean 6-seed server rerun but reverses in an earlier provenance variant. We therefore treat small-KG decoder choice as recipe- and provenance-sensitive rather than as a fixed dataset winner. We further show that decoder choice interacts with encoder depth on WN18RR, and that under our recipe L=0 ComplEx on YAGO3-10 reaches 0.6971 +/- 0.0048 MRR at d=128. The result is a compact audit protocol: report matched decoder rows, log small-KG provenance, and sweep decoder x depth before making encoder-level claims.

Xihang Shan, Ye Luo• 2026

Related benchmarks

TaskDatasetResultRank
Knowledge Graph CompletionWN18RR
Hits@145.8
185
Knowledge Graph CompletionFB15k-237
Hits@100.608
127
Knowledge Graph CompletionYAGO3-10
MRR0.697
5
Knowledge Graph CompletionCoDEx-m
MRR54.7
3
Knowledge Graph CompletionCoDEx-L
MRR54
2
Showing 5 of 5 rows

Other info

Follow for update