# Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models

arXiv: https://arxiv.org/abs/2408.06717 · HTML: https://mlsanity.com/paper/2408.06717/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 77 references that are in the map.
- First posted on arXiv 13 Aug 2024.

## Builds on (most cited first, 30 of 51)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [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)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks](https://mlsanity.com/paper/1810.02244/) (2018)
- [Large Language Models as Optimizers](https://mlsanity.com/paper/2309.03409/) (2023)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Geom-GCN: Geometric Graph Convolutional Networks](https://mlsanity.com/paper/2002.05287/) (2020)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [Graph Neural Networks with convolutional ARMA filters](https://mlsanity.com/paper/1901.01343/) (2019)
- [Design Space for Graph Neural Networks](https://mlsanity.com/paper/2011.08843/) (2020)
- [Meta-learning via Language Model In-context Tuning](https://mlsanity.com/paper/2110.07814/) (2021)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [Neural Predictor for Neural Architecture Search](https://mlsanity.com/paper/1912.00848/) (2019)
- [Mindstorms in Natural Language-Based Societies of Mind](https://mlsanity.com/paper/2305.17066/) (2023)

## Built on by (most cited first, 1 of 1)

- [Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design](https://mlsanity.com/paper/2507.15336/) (2025)

## Abstract (arXiv)

High-level automation is increasingly critical in AI, driven by rapid advances in large language models (LLMs) and AI agents. However, LLMs, despite their general reasoning power, struggle significantly in specialized, data-sensitive tasks such as designing Graph Neural Networks (GNNs). This difficulty arises from (1) the inherent knowledge gaps in modeling the intricate, varying relationships between graph properties and suitable architectures and (2) the external noise from misleading descriptive inputs, often resulting in generic or even misleading model suggestions. Achieving proficiency in designing data-aware models -- defined as the meta-level capability to systematically accumulate, interpret, and apply data-specific design knowledge -- remains challenging for existing automated approaches, due to their inefficient construction and application of meta-knowledge. To achieve meta-level proficiency, we propose DesiGNN, a knowledge-centered framework that systematically converts past model design experience into structured, fine-grained knowledge priors well-suited for meta-learning with LLMs. To account for the inherent variability and external noise, DesiGNN aligns empirical property filtering from extensive benchmarks with adaptive elicitation of literature insights via LLMs. By constructing a solid meta-knowledge between unseen graph understanding and known effective architecture patterns, DesiGNN can deliver top-5.77% initial model proposals for unseen datasets within seconds and achieve consistently superior performance with minimal search cost compared to baselines.