通过统一配方对比解码器，揭示知识图谱补全中解码器选择的关键影响。
Recipe-Controlled Decoder Audit for Structural Knowledge-Graph Completion
- 用相同训练配方切换解码器，评估其对性能的影响。
- 小数据集上解码器差异可达0.143 MRR，且结果受数据版本影响。
- 建议先调解码器与深度，再比较编码器效果，避免误判。
我们提出一种配方控制的解码器审计（RCDA）方法，用于结构化归纳式知识图谱补全（KGC）。该方法通过一个简单问题来检验：在相同训练配方下，更换解码器会带来哪些变化？以ComplEx和DistMult为主控组合，辅以RotatE/TransE的定点检查，我们在七个基准上进行评估。在五个标准知识图谱上，ComplEx与DistMult的差异虽小但稳定（MRR提升+0.005至+0.012）；而CompGCN风格编码器的效果则因数据集而异。在小规模知识图谱上，解码器的影响成为主要诊断因素：Kinship数据集显示ComplEx优势稳定达+0.143 MRR（6次种子实验），而UMLS在干净重跑中显示+0.022 MRR优势，但在早期溯源版本中则反转。因此，小规模数据集上的解码器选择应被视为配方与溯源敏感，而非固定优劣。我们进一步发现解码器选择与编码器深度在WN18RR上存在交互效应，并在本配方下，当深度d=128时，L=0的ComplEx在YAGO3-10上达到0.6971±0.0048 MRR。最终形成一套简洁审计协议：报告匹配解码器的性能行、记录小数据集的溯源信息、在做出编码器层面结论前，先扫描解码器与深度组合。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。