# TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning

arXiv: https://arxiv.org/abs/2309.13885 · HTML: https://mlsanity.com/paper/2309.13885/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 68 references that are in the map.
- First posted on arXiv 25 Sep 2023.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [DeBERTa: Decoding-enhanced BERT with Disentangled Attention](https://mlsanity.com/paper/2006.03654/) (2020)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction](https://mlsanity.com/paper/2106.06935/) (2021)
- [Inductive Relation Prediction by Subgraph Reasoning](https://mlsanity.com/paper/1911.06962/) (2019)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (2022)
- [Graph Neural Networks with Heterophily](https://mlsanity.com/paper/2009.13566/) (2020)

## Built on by (most cited first, 12 of 12)

- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Graph Foundation Models: Concepts, Opportunities and Challenges](https://mlsanity.com/paper/2310.11829/) (2023)
- [A Survey of Graph Meets Large Language Model: Progress and Future Directions](https://mlsanity.com/paper/2311.12399/) (2023)
- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning](https://mlsanity.com/paper/2406.16321/) (2024)
- [Large Language Model Meets Graph Neural Network in Knowledge Distillation](https://mlsanity.com/paper/2402.05894/) (2024)
- [Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection](https://mlsanity.com/paper/2507.11997/) (2025)
- [GTool: Graph Enhanced Tool Planning with Large Language Model](https://mlsanity.com/paper/2508.12725/) (2025)
- [LinkGPT: Teaching Large Language Models To Predict Missing Links](https://mlsanity.com/paper/2406.04640/) (2024)
- [Understanding GNNs and Homophily in Dynamic Node Classification](https://mlsanity.com/paper/2504.20421/) (2025)
- [Multimodal Graph Representation Learning with Dynamic Information Pathways](https://mlsanity.com/paper/2603.09258/) (2026)
- [Privately Learning from Graphs with Applications in Fine-tuning Large Language Models](https://mlsanity.com/paper/2410.08299/) (2024)

## Abstract (arXiv)

How can we enhance the node features acquired from Pretrained Models (PMs) to better suit downstream graph learning tasks? Graph Neural Networks (GNNs) have become the state-of-the-art approach for many high-impact, real-world graph applications. For feature-rich graphs, a prevalent practice involves utilizing a PM directly to generate features, without incorporating any domain adaptation techniques. Nevertheless, this practice is suboptimal because the node features extracted from PM are graph-agnostic and prevent GNNs from fully utilizing the potential correlations between the graph structure and node features, leading to a decline in GNNs performance. In this work, we seek to improve the node features obtained from a PM for downstream graph tasks and introduce TOUCHUP-G, which has several advantages. It is (a) General: applicable to any downstream graph task, including link prediction which is often employed in recommender systems; (b) Multi-modal: able to improve raw features of any modality (e.g. images, texts, audio); (c) Principled: it is closely related to a novel metric, feature homophily, which we propose to quantify the potential correlations between the graph structure and node features and we show that TOUCHUP-G can effectively shrink the discrepancy between the graph structure and node features; (d) Effective: achieving state-of-the-art results on four real-world datasets spanning different tasks and modalities.