发表机构
Iowa State University; BRAC University; University of Delaware（爱荷华州立大学; BRAC大学; 特拉华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FlowNeg是一种GFlowNet引导的知识图谱嵌入难负采样方法，在多个基准实验中，其MRR显著优于EMU和IF-NS，具有高梯度信息性与低冲突的优势。
AI 中文摘要
负采样决定知识图谱嵌入（KGE）模型是从有信息的反例中学习，还是在不可信的损坏样本上浪费更新。均匀负样本多样但简单，而难负采样器集中于少数实体，与保留的正样本冲突更多。我们提出FlowNeg，一种上下文条件分层生成流网络，它对与奖励成比例的采样进行摊销，无需在实体集上归一化复合奖励：给定一个正三元组和损坏侧，它先选择类型，再选择实体。其终端奖励结合了基于有界模型的难样本度，以及仅用于训练的、针对保留正样本冲突的结构分数，且基于特定关系的类型兼容支持。我们推导了奖励，对标准轨迹平衡进行了专门化，并以乘法方式界定了残差不平衡对终端和模式概率的扰动。在包含5种架构和5种基准的5种子的描述性网格实验中，FlowNeg在25个单元中有24个的平均MRR高于EMU和IF-NS（平均分别提升0.0172和0.0160）。另一项针对FB15k-237/RotatE的15种子对照实验，固定负样本数量、诊断预算和计算资源，结果显示FlowNeg的MRR为0.359±0.001，而EMU为0.346±0.002，FlowNeg具有接近均匀的固定划分多样性、高梯度信息性和低冲突。该证据支持覆盖模式的负样本生成，无需将结构相似性视为开放世界的真理 oracle。
英文摘要
Negative sampling determines whether a knowledge graph embedding (KGE) model learns from informative counterexamples or wastes updates on implausible corruptions. Uniform negatives are diverse but easy, whereas hard-negative miners concentrate on few entities and collide more with held-out positives. We introduce FlowNeg, a context-conditioned hierarchical generative flow network that amortizes reward-proportional sampling without normalizing a composite reward over the entity set: given a positive triple and corruption side, it selects a type, then an entity. Its terminal reward combines bounded model-based hardness with a training-only structural score for held-out-positive collision, over a relation-specific type-compatible support. We derive the reward, specialize standard trajectory balance, and bound multiplicatively how residual imbalance perturbs terminal and mode probability. Across a descriptive five-seed grid of five architectures and five benchmarks, FlowNeg has higher mean MRR than EMU and than IF-NS in 24 of 25 cells ($+0.0172$ and $+0.0160$ on average). A separate 15-seed FB15k-237/RotatE control fixing negative count, diagnostic budget, and compute gives FlowNeg $0.359\pm0.001$ MRR against $0.346\pm0.002$ for EMU, with near-uniform fixed-partition diversity, high gradient informativeness, and low collision. The evidence supports mode-covering negative generation without treating structural similarity as an open-world truth oracle.
Comments20 pages, 1 figure
