# Structure Aware Negative Sampling in Knowledge Graphs

arXiv: https://arxiv.org/abs/2009.11355 · HTML: https://mlsanity.com/paper/2009.11355/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 26 of 26)

- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling](https://mlsanity.com/paper/2209.07084/) (2022)
- [Does Negative Sampling Matter? A Review with Insights into its Theory and Applications](https://mlsanity.com/paper/2402.17238/) (2024)
- [Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion](https://mlsanity.com/paper/2205.00904/) (2022)
- [Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning](https://mlsanity.com/paper/2206.10140/) (2022)
- [SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2210.04870/) (2022)
- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [Diffusion-based Negative Sampling on Graphs for Link Prediction](https://mlsanity.com/paper/2403.17259/) (2024)
- [Modality-Aware Negative Sampling for Multi-modal Knowledge Graph Embedding](https://mlsanity.com/paper/2304.11618/) (2023)
- [Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embedding](https://mlsanity.com/paper/2310.09781/) (2023)
- [MixKG: Mixing for harder negative samples in knowledge graph](https://mlsanity.com/paper/2202.09606/) (2022)
- [Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding](https://mlsanity.com/paper/2210.06242/) (2022)
- [Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning](https://mlsanity.com/paper/2407.12703/) (2024)
- [HaSa: Hardness and Structure-Aware Contrastive Knowledge Graph Embedding](https://mlsanity.com/paper/2305.10563/) (2023)
- [LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings](https://mlsanity.com/paper/2203.04703/) (2022)
- [Subsampling for Knowledge Graph Embedding Explained](https://mlsanity.com/paper/2209.12801/) (2022)
- [Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning](https://mlsanity.com/paper/2306.07512/) (2023)
- [Importance of negative sampling in weak label learning](https://mlsanity.com/paper/2309.13227/) (2023)
- [Diffusion-based Hierarchical Negative Sampling for Multimodal Knowledge Graph Completion](https://mlsanity.com/paper/2501.15393/) (2025)
- [Optimal Embedding Guided Negative Sample Generation for Knowledge Graph Link Prediction](https://mlsanity.com/paper/2504.03327/) (2025)
- [Two-dimensional Taxonomy for N-ary Knowledge Representation Learning Methods](https://mlsanity.com/paper/2506.05626/) (2025)
- [Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning](https://mlsanity.com/paper/2211.03950/) (2022)
- [Not All Negatives Are Worth Attending to: Meta-Bootstrapping Negative Sampling Framework for Link Prediction](https://mlsanity.com/paper/2312.04815/) (2023)
- [Unified Interpretation of Smoothing Methods for Negative Sampling Loss Functions in Knowledge Graph Embedding](https://mlsanity.com/paper/2407.04251/) (2024)
- [Diversified and Adaptive Negative Sampling on Knowledge Graphs](https://mlsanity.com/paper/2410.07592/) (2024)
- [FlowNeg: GFlowNet-Guided Diverse Hard Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/2608.23849/) (2026)

## Abstract (arXiv)

Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node's k-hop neighborhood. Empirically, we demonstrate that SANS finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization.