---
title: "How Many and How Much? Contrastive Learning with Negative Samples for Knowledge Graph Embedding"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.37389v1"
permalink: "https://feed.astralor.com/items/itm_9b39b2e94557a49a416dc8c7"
published: "2026-10-27T15:12:54.000Z"
score: 54
channel: "tech"
tags: ["RAG","How Many","How Much","Contrastive Learning","Negative Samples","Knowledge Graph Embedding","Knowledge","KGE"]
---

# How Many and How Much? Contrastive Learning with Negative Samples for Knowledge Graph Embedding

## 速览

Knowledge graph embedding (KGE), a fundamental technique for knowledge-centric Web and KG-augmented AI applications, is commonly trained through contrastive learning with negative samples to learn discriminative represe…

## 关键点

- Knowledge graph embedding (KGE), a fundamental technique for knowledge-centric Web and KG-augmented AI applications, is commonly trained through contrastive learning with negative samples to learn discriminative represe…
- Despite its empirical success, two crucial questions regarding negative samples remain underexplored: (Q1) how many negative samples should be used for each positive sample and (Q2) how much should each negative sample …
- To answer these questions, we propose RADAR, a novel contrastive learning framework for KGE models with two effective strategies, respectively: (1) Risk-aware negative budget allocation quantifies false-negative samplin…

## 全文

Knowledge graph embedding (KGE), a fundamental technique for knowledge-centric Web and KG-augmented AI applications, is commonly trained through contrastive learning with negative samples to learn discriminative representations. Despite its empirical success, two crucial questions regarding negative samples remain underexplored: (Q1) how many negative samples should be used for each positive sample and (Q2) how much should each negative sample contribute to learning? To answer these questions, we propose RADAR, a novel contrastive learning framework for KGE models with two effective strategies, respectively: (1) Risk-aware negative budget allocation quantifies false-negative sampling risk by modeling an open-world KG as a stochastic partial observation of its closed-world counterpart and adaptively assigns a negative budget to each positive sample based on its risk; (2) Distribution-calibrated negative weighting assigns negative weights by calibrating the weighting strength for each positive based on two complementary characteristics of the negative-score distribution: dispersion and concentration. Extensive experiments on 3 real-world KGs with 4 KGE models reveal that RADAR achieves the best KGE performance on average across all model--KG combinations and reduces sampled false negatives by over 90% compared with conventional fixed-budget methods.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_9b39b2e94557a49a416dc8c7