TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations
Text-Attributed Graphs (TAGs) enhance graph structures with natural language descriptions, enabling detailed representation of data and their relationships across a broad spectrum of real-world scenarios. Despite the potential for deeper insights, existing TAG representation learning primarily relies on supervised methods, necessitating extensive labeled data and limiting applicability across diverse contexts. This paper introduces a new self-supervised learning framework, Text-And-Graph Multi-View Alignment (TAGA), which overcomes these constraints by integrating TAGs' structural and semantic dimensions. TAGA constructs two complementary views: Text-of-Graph view, which organizes node texts into structured documents based on graph topology, and the Graph-of-Text view, which converts textual nodes and connections into graph data. By aligning representations from both views, TAGA captures joint textual and structural information. In addition, a novel structure-preserving random walk algorithm is proposed for efficient training on large-sized TAGs. Our framework demonstrates strong performance in zero-shot and few-shot scenarios across eight real-world datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSelf-Supervised LearningTAGSimilar Papers 제목 키워드 기반
GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. Howeve…
Contrastive LearningGraph Neural NetworkLanguage ModelingLanguage Modelling+2MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detection
Graph anomaly detection has long been an important problem in various domains pertaining to information security such as financial fraud, social spam and network intrusion. The majority of existing methods are performed …
Anomaly DetectionFew-Shot LearningGraph Anomaly DetectionMeta-Learning+1TAGA: Self-supervised Learning for Template-free Animatable Gaussian Articulated Model
Decoupling from customized parametric templates represents a crucial step toward the creation of fully flexible, animatable articulated models. While existing template-free methods can achieve high-fidelity reconstru…
Anomaly DetectionSelf-Supervised LearningBenchmarking zero-shot and few-shot approaches for tokenization, tagging, and dependency parsing of Tagalog text
The grammatical analysis of texts in any written language typically involves a number of basic processing tasks, such as tokenization, morphological tagging, and dependency parsing. State-of-the-art systems can achieve h…
BenchmarkingData AugmentationDependency ParsingMorphological Tagging+1Self-supervised Contrastive Attributed Graph Clustering
Attributed graph clustering, which learns node representation from node attribute and topological graph for clustering, is a fundamental but challenging task for graph analysis. Recently, methods based on graph contrasti…
AttributeClusteringContrastive LearningGraph Clustering+1