arXiv cs.AI· Chang Won Kim, Jaewook Lee, Haeun Min, JunNyeong Jeong, Minwoo Sim, Barom Kang, Kyohoon Jin·· 4 小时前AI 评分31
KG-Neighbor：知识引导的邻域图构建方法提升嵌入可视化
KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization
AI 导读
论文提出知识引导邻域图构建方法 KGN，将每条实例的关系知识表示为知识图谱三元组，以三元组共享程度调整嵌入距离并重建 top-k 邻域图，全程不使用类别标签。在八组文本与图像数据集-编码器条件下，最大 NMI 和 LT_2D 均超过 kNN 基线，最大提升分别达 0.68 和 1.35。配套的 IDProfile（IDP）分析表明，残余不匹配不应自动被解读为投影失败。
正文 · 原文
Abstract:In embedding visualizations, nearby instances are interpreted as semantically related, although neighborhoods derived from input embeddings may not reflect content relationships. Neighborhood-based dimensionality reduction (DR) methods can propagate this limitation by optimizing layouts from embedding-based neighborhood graphs. We propose Knowledge-Guided Neighborhood Graph Construction (KGN), which represents relational knowledge derived from each instance as a set of knowledge graph (KG) triples. It uses the degree of triple sharing as pairwise semantic evidence to adjust embedding distances and reconstruct the top-k neighborhood graph; neither KG extraction nor neighborhood construction uses class labels. We also introduce IDProfile (IDP), which interprets residual mismatches by independently assessing whether the source content supports the assigned class label and the neighborhood-majority class. Across eight text and image dataset-encoder conditions, we characterize KGN over the full guidance-strength sweep and four KG similarity measures. Across this sweep, the maximum NMI and LT_2D each exceed the corresponding kNN baseline in all eight conditions, with the largest gains reaching 0.68 and 1.35, respectively. The gains and the extent of neighborhood reconfiguration vary across conditions and are larger under encoder conditions with lower kNN baseline scores. The IDP analysis shows that the largest reductions are concentrated in Placement Issue candidates, whereas Label Issue and Unresolved Case instances account for a larger share of the remaining review set. These results indicate that KGN can narrow the evaluated gap between embedding-based neighborhoods and content-supported semantic relations, while IDP shows that a residual mismatch should not automatically be interpreted as a projection failure.
| Comments: | Accepted at WSDN 2027 findings |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07246 [cs.LG] |
| (or arXiv:2611.07246v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07246 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kyohoon Jin [view email]
[v1]
Wed, 4 Nov 2026 23:54:02 UTC (2,033 KB)
来源：arXiv cs.AI · arxiv.org