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

• URL: http://arxiv.org/abs/2408.06717v2
• Date: Mon, 21 Jul 2025 08:23:07 GMT
• Title: Proficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
• Authors: Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou,
• Abstract summary: DesiGNN is a knowledge-centered framework that converts past model design experiences into structured, fine-grained knowledge priors.<n>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.
• Score: 20.31388126105889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 the meta-level proficiency, we propose DesiGNN, a knowledge-centered framework that systematically converts past model design experiences into structured, fine-grained knowledge priors well fitted to 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 costs against baselines.

Related papers

• Quantizing Text-attributed Graphs for Semantic-Structural Integration [6.721504414917793]
  Text-attributed graphs (TAGs) have emerged as a powerful representation for modeling complex relationships across diverse domains.<n>With the rise of large language models (LLMs), there is growing interest in leveraging their capabilities for graph learning.<n>We propose STAG, a novel self-supervised framework that directly quantizes graph structural information into discrete tokens using a frozen codebook.
  arXiv  Detail & Related papers  (2025-07-20T09:18:02Z)
• Do We Really Need GNNs with Explicit Structural Modeling? MLPs Suffice for Language Model Representations [50.45261187796993]
  Graph Neural Networks (GNNs) fail to fully utilize structural information, whereas Multi-Layer Perceptrons (MLPs) exhibit a surprising ability in structure-aware tasks.<n>This paper introduces a comprehensive probing framework from an information-theoretic perspective.
  arXiv  Detail & Related papers  (2025-06-26T18:10:28Z)
• Injecting Knowledge Graphs into Large Language Models [0.0]
  We build on encoding techniques which integrate graph embeddings within the Large Language Models as tokens.<n>Our approach is model-agnostic, resource-efficient, and compatible with any LLMs.
  arXiv  Detail & Related papers  (2025-05-12T13:31:26Z)
• Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models [3.8429489584622156]
  We propose CoGNNs-LLMEA, a framework that integrates a graph neural network with task-adaptive message passing and a large language model-enhanced evolutionary algorithm. As a predictive model, CoGNNs directly leverages intermediate representations generated from source code after compiler front-end processing, enabling prediction of quality of results (QoR) without invoking HLS tools. CoGNNs achieves state-of-the-art prediction accuracy in post-HLS QoR prediction, reducing mean prediction errors by 2.8$times$ for latency and 3.4$times$ for resource utilization compared to baseline models
  arXiv  Detail & Related papers  (2025-04-28T10:08:56Z)
• GNNMerge: Merging of GNN Models Without Accessing Training Data [12.607714697138428]
  Model merging has gained prominence in machine learning as a method to integrate multiple trained models into a single model without accessing the original training data. Existing approaches have demonstrated success in domains such as computer vision and NLP, their application to Graph Neural Networks (GNNs) remains unexplored. We propose GNNMerge, which utilizes a task-agnostic node embedding alignment strategy to merge GNNs.
  arXiv  Detail & Related papers  (2025-03-05T11:02:29Z)
• KaLM: Knowledge-aligned Autoregressive Language Modeling via Dual-view Knowledge Graph Contrastive Learning [74.21524111840652]
  This paper proposes textbfKaLM, a textitKnowledge-aligned Language Modeling approach.<n>It fine-tunes autoregressive large language models to align with KG knowledge via the joint objective of explicit knowledge alignment and implicit knowledge alignment.<n> Notably, our method achieves a significant performance boost in evaluations of knowledge-driven tasks.
  arXiv  Detail & Related papers  (2024-12-06T11:08:24Z)
• How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension [53.6373473053431]
  This work introduces a benchmark to assess large language models' capabilities in graph pattern tasks.<n>We have developed a benchmark that evaluates whether LLMs can understand graph patterns based on either terminological or topological descriptions.<n>Our benchmark encompasses both synthetic and real datasets, and a variety of models, with a total of 11 tasks and 7 models.
  arXiv  Detail & Related papers  (2024-10-04T04:48:33Z)
• Neurosymbolic AI approach to Attribution in Large Language Models [5.3454230926797734]
  Neurosymbolic AI (NesyAI) combines the strengths of neural networks with structured symbolic reasoning. This paper explores how NesyAI frameworks can enhance existing attribution models, offering more reliable, interpretable, and adaptable systems.
  arXiv  Detail & Related papers  (2024-09-30T02:20:36Z)
• LangTopo: Aligning Language Descriptions of Graphs with Tokenized Topological Modeling [10.907949155931474]
  We introduce LangTopo, which aligns graph structure modeling with natural language understanding at the token level. We demonstrate the effectiveness of our proposed method on multiple datasets.
  arXiv  Detail & Related papers  (2024-06-19T06:20:22Z)
• Unleash Graph Neural Networks from Heavy Tuning [33.948899558876604]
  Graph Neural Networks (GNNs) are deep-learning architectures designed for graph-type data. We propose a graph conditional latent diffusion framework (GNN-Diff) to generate high-performing GNNs directly by learning from checkpoints saved during a light-tuning coarse search.
  arXiv  Detail & Related papers  (2024-05-21T06:23:47Z)
• G-SAP: Graph-based Structure-Aware Prompt Learning over Heterogeneous Knowledge for Commonsense Reasoning [8.02547453169677]
  We propose a novel Graph-based Structure-Aware Prompt Learning Model for commonsense reasoning, named G-SAP. In particular, an evidence graph is constructed by integrating multiple knowledge sources, i.e. ConceptNet, Wikipedia, and Cambridge Dictionary. The results reveal a significant advancement over the existing models, especially, with 6.12% improvement over the SoTA LM+GNNs model on the OpenbookQA dataset.
  arXiv  Detail & Related papers  (2024-05-09T08:28:12Z)
• ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph [142.42275983201978]
  We propose a subgraph-aware self-attention mechanism to imitate the GNN for performing structured reasoning. We also adopt an adaptation tuning strategy to adapt the model parameters with 20,000 subgraphs with synthesized questions. Experiments show that ReasoningLM surpasses state-of-the-art models by a large margin, even with fewer updated parameters and less training data.
  arXiv  Detail & Related papers  (2023-12-30T07:18:54Z)
• Enabling Accelerators for Graph Computing [0.0]
  Graph Neural Networks (GNNs) offer a novel paradigm for learning on graph-structured data. GNNs present new computational challenges compared to conventional neural networks. This thesis aims to develop a better understanding of how GNNs interact with the underlying hardware.
  arXiv  Detail & Related papers  (2023-12-16T23:31:20Z)
• Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty [52.72790059506241]
  Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text. Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
  arXiv  Detail & Related papers  (2023-09-07T01:35:24Z)
• Characterizing the Efficiency of Graph Neural Network Frameworks with a Magnifying Glass [10.839902229218577]
  Graph neural networks (GNNs) have received great attention due to their success in various graph-related learning tasks. Recent GNNs have been developed with different graph sampling techniques for mini-batch training of GNNs on large graphs. It is unknown how much the frameworks are 'eco-friendly' from a green computing perspective.
  arXiv  Detail & Related papers  (2022-11-06T04:22:19Z)
• Schema-aware Reference as Prompt Improves Data-Efficient Knowledge Graph Construction [57.854498238624366]
  We propose a retrieval-augmented approach, which retrieves schema-aware Reference As Prompt (RAP) for data-efficient knowledge graph construction. RAP can dynamically leverage schema and knowledge inherited from human-annotated and weak-supervised data as a prompt for each sample.
  arXiv  Detail & Related papers  (2022-10-19T16:40:28Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• Edge-featured Graph Neural Architecture Search [131.4361207769865]
  We propose Edge-featured Graph Neural Architecture Search to find the optimal GNN architecture. Specifically, we design rich entity and edge updating operations to learn high-order representations. We show EGNAS can search better GNNs with higher performance than current state-of-the-art human-designed and searched-based GNNs.
  arXiv  Detail & Related papers  (2021-09-03T07:53:18Z)
• Design Space for Graph Neural Networks [81.88707703106232]
  We study the architectural design space for Graph Neural Networks (GNNs) which consists of 315,000 different designs over 32 different predictive tasks. Our key results include: (1) A comprehensive set of guidelines for designing well-performing GNNs; (2) while best GNN designs for different tasks vary significantly, the GNN task space allows for transferring the best designs across different tasks; (3) models discovered using our design space achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-11-17T18:59:27Z)
• Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks [55.98291376393561]
  Graph neural networks (GNNs) have emerged as a powerful tool for learning software engineering tasks. Recurrent neural networks (RNNs) are well-suited to long sequential chains of reasoning, but they do not naturally incorporate program structure. We introduce a novel GNN architecture, the Instruction Pointer Attention Graph Neural Networks (IPA-GNN), which improves systematic generalization on the task of learning to execute programs.
  arXiv  Detail & Related papers  (2020-10-23T19:12:30Z)
• NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis [53.106414896248246]
  We present a framework that allows analysts to effectively build the solution sub-graph space and guide the network search by injecting their domain knowledge. Applying this technique in an iterative manner allows analysts to converge to the best performing neural network architecture for a given application.
  arXiv  Detail & Related papers  (2020-09-28T01:48:45Z)
• Architectural Implications of Graph Neural Networks [17.01480604968118]
  Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures. GNN is not as well understood in the system and architecture community as its counterparts such as multi-layer perceptrons and convolutional neural networks.
  arXiv  Detail & Related papers  (2020-09-02T03:36:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.