Exploiting Text Semantics for Few and Zero Shot Node Classification on Text-attributed Graph
Not on the map. Why?
Abstract (arXiv)
Text-attributed graph (TAG) provides a text description for each graph node, and few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. Existing work utilizes various graph-based augmentation techniques to train the node and text embeddings, while text-based augmentations are largely unexplored. In this paper, we propose Text Semantics Augmentation (TSA) to improve accuracy by introducing more text semantic supervision signals. Specifically, we design two augmentation techniques, i.e., positive semantics matching and negative semantics contrast, to provide more reference texts for each graph node or text description. Positive semantic matching retrieves texts with similar embeddings to match with a graph node. Negative semantic contrast adds a negative prompt to construct a text description with the opposite semantics, which is contrasted with the original node and text. We evaluate TSA on 5 datasets and compare with 13 state-of-the-art baselines. The results show that TSA consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 13 May 2025.
Builds on
27 of 42 references.
References · 27
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
- 2020Graph Contrastive Learning with Augmentationscited by 1,208
- 2018Deep Graph Infomaxcited by 1,106
- 2020Debiased Contrastive Learningcited by 356
- 2018Graph Convolutional Networks for Text Classificationcited by 345
- 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
15 more
- 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 301
- 2023Exploring the Potential of Large Language Models (LLMs) in Learning on Graphscited by 274
- 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 226
- 2023GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networkscited by 167
- 2021InfoGCL: Information-Aware Graph Contrastive Learningcited by 105
- 2022Universal Prompt Tuning for Graph Neural Networkscited by 100
- 2023Label-free Node Classification on Graphs with Large Language Models (LLMS)cited by 72
- 2024GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Taskscited by 63
- 2023Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Promptingcited by 62
- 2021Prototypical Graph Contrastive Learningcited by 37
- 2023Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphscited by 23
- 2020Enhancing Social Recommendation with Adversarial Graph Convolutional Networkscited by 16
- 2024Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphscited by 11
- 2023Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learningcited by 9
- 2024Towards Scalable and Deep Graph Neural Networks via Noise Maskingcited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.