# Subgraph-Aware Training of Language Models for Knowledge Graph Completion Using Structure-Aware Contrastive Learning

arXiv: https://arxiv.org/abs/2407.12703 · HTML: https://mlsanity.com/paper/2407.12703/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 57 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation](https://mlsanity.com/paper/1911.06136/) (2019)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [CERT: Contrastive Self-supervised Learning for Language Understanding](https://mlsanity.com/paper/2005.12766/) (2020)
- [Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax](https://mlsanity.com/paper/2006.10408/) (2020)
- [Balanced Contrastive Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.09052/) (2022)
- [Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective](https://mlsanity.com/paper/2003.10780/) (2020)
- [SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models](https://mlsanity.com/paper/2203.02167/) (2022)
- [Understanding Negative Sampling in Graph Representation Learning](https://mlsanity.com/paper/2005.09863/) (2020)
- [Inductive Entity Representations from Text via Link Prediction](https://mlsanity.com/paper/2010.03496/) (2020)
- [Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings](https://mlsanity.com/paper/1704.07130/) (2017)
- [Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax](https://mlsanity.com/paper/1902.08564/) (2019)
- [Structure Aware Negative Sampling in Knowledge Graphs](https://mlsanity.com/paper/2009.11355/) (2020)
- [Contrastive Learning of Sentence Embeddings from Scratch](https://mlsanity.com/paper/2305.15077/) (2023)
- [Toward Degree Bias in Embedding-Based Knowledge Graph Completion](https://mlsanity.com/paper/2302.05044/) (2023)
- [KRACL: Contrastive Learning with Graph Context Modeling for Sparse Knowledge Graph Completion](https://mlsanity.com/paper/2208.07622/) (2022)

## Built on by (most cited first, 4 of 4)

- [GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion](https://mlsanity.com/paper/2502.11471/) (2025)
- [Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding](https://mlsanity.com/paper/2508.02426/) (2025)
- [Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers](https://mlsanity.com/paper/2512.10422/) (2025)
- [Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling](https://mlsanity.com/paper/2605.27023/) (2026)

## Abstract (arXiv)

Fine-tuning pre-trained language models (PLMs) has recently shown a potential to improve knowledge graph completion (KGC). However, most PLM-based methods focus solely on encoding textual information, neglecting the long-tailed nature of knowledge graphs and their various topological structures, e.g., subgraphs, shortest paths, and degrees. We claim that this is a major obstacle to achieving higher accuracy of PLMs for KGC. To this end, we propose a Subgraph-Aware Training framework for KGC (SATKGC) with two ideas: (i) subgraph-aware mini-batching to encourage hard negative sampling and to mitigate an imbalance in the frequency of entity occurrences during training, and (ii) new contrastive learning to focus more on harder in-batch negative triples and harder positive triples in terms of the structural properties of the knowledge graph. To the best of our knowledge, this is the first study to comprehensively incorporate the structural inductive bias of the knowledge graph into fine-tuning PLMs. Extensive experiments on three KGC benchmarks demonstrate the superiority of SATKGC. Our code is available.