# GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism

arXiv: https://arxiv.org/abs/2404.06911 · HTML: https://mlsanity.com/paper/2404.06911/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 61 references that are in the map.
- First posted on arXiv 10 Apr 2024.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters](https://mlsanity.com/paper/2002.01808/) (2020)
- [Knowledge Enhanced Contextual Word Representations](https://mlsanity.com/paper/1909.04164/) (2019)
- [Translation between Molecules and Natural Language](https://mlsanity.com/paper/2204.11817/) (2022)
- [GreaseLM: Graph REASoning Enhanced Language Models for Question Answering](https://mlsanity.com/paper/2201.08860/) (2022)
- [Text Generation from Knowledge Graphs with Graph Transformers](https://mlsanity.com/paper/1904.02342/) (2019)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Model](https://mlsanity.com/paper/1912.09637/) (2019)
- [Graph-to-Sequence Learning using Gated Graph Neural Networks](https://mlsanity.com/paper/1806.09835/) (2018)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [FactKG: Fact Verification via Reasoning on Knowledge Graphs](https://mlsanity.com/paper/2305.06590/) (2023)
- [A Graph-to-Sequence Model for AMR-to-Text Generation](https://mlsanity.com/paper/1805.02473/) (2018)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm](https://mlsanity.com/paper/2104.08682/) (2021)
- [GPT-too: A language-model-first approach for AMR-to-text generation](https://mlsanity.com/paper/2005.09123/) (2020)
- [Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity](https://mlsanity.com/paper/2004.06577/) (2020)
- [Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2001.11003/) (2020)

## Built on by (most cited first, 2 of 2)

- [MGSA: Multi-Granularity Graph Structure Attention for Knowledge Graph-to-Text Generation](https://mlsanity.com/paper/2409.10294/) (2024)
- [GMLM: Bridging Graph Neural Networks and Language Models for Heterophilic Node Classification](https://mlsanity.com/paper/2503.05763/) (2025)

## Abstract (arXiv)

Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks. However, bridging the modality gap between graph structures and text remains a significant challenge. Traditional methods like linearizing graphs for PLMs lose vital graph connectivity, whereas Graph Neural Networks (GNNs) require cumbersome processes for integration into PLMs. In this work, we propose a novel graph-guided self-attention mechanism, GraSAME. GraSAME seamlessly incorporates token-level structural information into PLMs without necessitating additional alignment or concatenation efforts. As an end-to-end, lightweight multimodal module, GraSAME follows a multi-task learning strategy and effectively bridges the gap between graph and textual modalities, facilitating dynamic interactions between GNNs and PLMs. Our experiments on the graph-to-text generation task demonstrate that GraSAME outperforms baseline models and achieves results comparable to state-of-the-art (SOTA) models on WebNLG datasets. Furthermore, compared to SOTA models, GraSAME eliminates the need for extra pre-training tasks to adjust graph inputs and reduces the number of trainable parameters by over 100 million.