Metraipolis › archive › dc_76abc7ebb716

FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding — arXiv:2608.23849

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23849
License (as archived)
CC0-1.0
Archived
2026-10-18T06:35:38.774Z
SHA-256 of the archived text
7e22f46ec1aa1b5f1ebf7ec32d4f56bcaaefe5c4fb81c897dd250500e8fc2194
Stable URL of this page
https://metraipolis.com/documento/dc_76abc7ebb716

How to cite

FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding — arXiv:2608.23849 — arXiv (en), https://arxiv.org/abs/2608.23849 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76abc7ebb716 (Metraipolis archive dc_76abc7ebb716, sha256 7e22f46ec1aa1b5f1ebf7ec32d4f56bcaaefe5c4fb81c897dd250500e8fc2194)
BibTeX
@misc{dc76abc7ebb716,
  title = {FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding — arXiv:2608.23849},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23849},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76abc7ebb716; sha256 7e22f46ec1aa1b5f1ebf7ec32d4f56bcaaefe5c4fb81c897dd250500e8fc2194},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23849. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23849 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:28:52.193Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).