paper-with-me

Papers

Deep Semantic Graph Learning via LLM based Node Enhancement

2025-02-11 · Chuanqi Shi, Yiyi Tao, Hang Zhang, Lun Wang, Shaoshuai Du, Yixian Shen, Yanxin Shen

Graph learning has attracted significant attention due to its widespread real-world applications. Current mainstream approaches rely on text node features and obtain initial node embeddings through shallow embedding learning using GNNs, which shows limitations in capturing deep textual semantics. Recent advances in Large Language Models (LLMs) have demonstrated superior capabilities in understanding text semantics, transforming traditional text feature processing. This paper proposes a novel framework that combines Graph Transformer architecture with LLM-enhanced node features. Specifically, we leverage LLMs to generate rich semantic representations of text nodes, which are then processed by a multi-head self-attention mechanism in the Graph Transformer to capture both local and global graph structural information. Our model utilizes the Transformer's attention mechanism to dynamically aggregate neighborhood information while preserving the semantic richness provided by LLM embeddings. Experimental results demonstrate that the LLM-enhanced node features significantly improve the performance of graph learning models on node classification tasks. This approach shows promising results across multiple graph learning tasks, offering a practical direction for combining graph networks with language models.

📄 PDF Abstract BibTeX arXiv:2502.07982

Code (0)

등록된 구현이 없습니다.

Tasks

Graph LearningNode Classification

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
LapEigen 설명 없음

Similar Papers 제목 키워드 기반

SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing

2026-05-04 · Genhao Tian, Taihua Xu, Shuyin Xia, Qinghua Zhang 외 arxiv

Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on $k$-nearest neighbors ($k$NN) or other node-level full search algorithms (FSA) to m…

Graph Representation LearningGraph Neural Network

Structure-Aware Label Smoothing for Graph Neural Networks

2021-12-01 · Yiwei Wang, Yujun Cai, Yuxuan Liang, Wei Wang 외

Representing a label distribution as a one-hot vector is a common practice in training node classification models. However, the one-hot representation may not adequately reflect the semantic characteristics of a node in …

ClassificationNode Classification

Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network

2024-03-26 · Yilun Zheng, Jiahao Xu, Lihui Chen

Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal performance. Current studies on graph heterophi…

Graph LearningGraph Neural NetworkNode Classification

When Product Search Meets Collaborative Filtering: A Hierarchical Heterogeneous Graph Neural Network Approach

2021-08-17 · Xiangkun Yin, Yangyang Guo, Liqiang Nie, Zhiyong Cheng

Personalization lies at the core of boosting the product search system performance. Prior studies mainly resorted to the semantic matching between textual queries and user/product related documents, leaving the user coll…

Collaborative FilteringGraph Neural NetworkRepresentation LearningSentence

PAD: a graphical and numerical enhancement of structural coding to facilitate thematic analysis of a literature corpus

2021-07-26 · Etienne-Victor Depasquale, Humaira Abdul Salam, Franco Davoli

We suggest an enhancement to structural coding through the use of (a) causally bound codes, (b) basic constructs of graph theory and (c) statistics. As is the norm with structural coding, the codes are collected into cat…