Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
The paper discusses an innovative approach to improve Knowledge Graph Foundation Models (KGFMs) through enhanced negative sampling. The proposed method, KMAS, constructs hard negative triples to provide better training supervision for KGFMs. Experimental results indicate that this method can significantly enhance the performance of KGFMs without requiring excessive computational resources.
- ▪Knowledge graphs are essential for tasks like question answering and recommender systems but often lack completeness.
- ▪The KMAS method dynamically adjusts the ratio of hard negative triples during training to improve model performance.
- ▪Extensive experiments on 44 datasets show that KMAS enhances state-of-the-art KGFMs efficiently.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2605.27023 |
| Publication time | Wed, 27 May 2026 00:00:00 -0400 |
| Retrieval time | 2026-05-27T04:07:56.398Z |
| Last seen | 2026-05-27T04:07:56.398Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | CQjouqVNXIry |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.27023 (cs) [Submitted on 26 May 2026] Title:Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling Authors:Yinan Liu, Wenjin Xu, Zhiyuan Zha, Xiaochun Yang, Bin Wang View a PDF of the paper titled Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling, by Yinan Liu and 4 other authors View PDF HTML (experimental) Abstract:Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are often very incomplete.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
