Metraipolis › archive › dc_10f1cc536bb4

From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion — arXiv:2610.39114

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39114
License (as archived)
CC0-1.0
Archived
2026-10-31T06:13:05.773Z
SHA-256 of the archived text
dab469429f8509641dc7a3f65ebe0b692239347359242e52454e861c4a4c6184
Stable URL of this page
https://metraipolis.com/documento/dc_10f1cc536bb4

How to cite

From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion — arXiv:2610.39114 — arXiv (en), https://arxiv.org/abs/2610.39114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_10f1cc536bb4 (Metraipolis archive dc_10f1cc536bb4, sha256 dab469429f8509641dc7a3f65ebe0b692239347359242e52454e861c4a4c6184)
BibTeX
@misc{dc10f1cc536bb4,
  title = {From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion — arXiv:2610.39114},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39114},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_10f1cc536bb4; sha256 dab469429f8509641dc7a3f65ebe0b692239347359242e52454e861c4a4c6184},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Triple set prediction (TSP) is to recover missing relational triples in a knowledge graph by predicting the triple set instead of isolated links. Existing approaches predominantly rely on the subgraph-based completion paradigm, where the original graph is first partitioned into local subgraphs which are then independently completed. Such a paradigm suffers from fragmented structural reasoning, limited cross subgraph dependency modeling, and missing predictions across subgraphs. This paper proposes LatentDiff, a novel unified latent generative framework for TSP, which reformulates knowledge graph completion as latent space graph generation. LatentDiff first learns a compact latent representation using a relation-aware residual-quantized knowledge graph autoencoder, which encodes the whole graph into relation-aware latent embeddings, quantizes them with chunked residual codebooks, and reconstructs triples through a factorized decoder. On top of this latent space, we introduce an observation-anchored latent graph diffusion model, where the target latent graph representation is perturbed toward the observed latent. The reverse process recovers missing triples through progressive latent denoising. Experiments on three benchmark datasets show that LatentDiff outperforms the SOTA in terms of F_{tsp} by 5.4 percentage points on average. Code: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.39114 — 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 2026-10-31T06:07:08.698Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).