# Hound: Hunting Supervision Signals for Few and Zero Shot Node Classification on Text-attributed Graph

arXiv: https://arxiv.org/abs/2409.00727 · HTML: https://mlsanity.com/paper/2409.00727/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 1 Sep 2024.

## Builds on (most cited first, 27 of 27)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks](https://mlsanity.com/paper/2110.07602/) (2021)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [GPT-GNN: Generative Pre-Training of Graph Neural Networks](https://mlsanity.com/paper/2006.15437/) (2020)
- [Learning on Large-scale Text-attributed Graphs via Variational Inference](https://mlsanity.com/paper/2210.14709/) (2022)
- [GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph](https://mlsanity.com/paper/2105.02605/) (2021)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Meta-GNN: On Few-shot Node Classification in Graph Meta-learning](https://mlsanity.com/paper/1905.09718/) (2019)
- [Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting](https://mlsanity.com/paper/2305.03324/) (2023)
- [Task-Adaptive Few-shot Node Classification](https://mlsanity.com/paper/2206.11972/) (2022)
- [Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2309.02848/) (2023)
- [Enhancing Social Recommendation with Adversarial Graph Convolutional Networks](https://mlsanity.com/paper/2004.02340/) (2020)
- [Zero-shot Node Classification with Decomposed Graph Prototype Network](https://mlsanity.com/paper/2106.08022/) (2021)
- [Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs](https://mlsanity.com/paper/2407.15431/) (2024)

## Built on by (most cited first, 2 of 2)

- [Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications](https://mlsanity.com/paper/2510.21131/) (2025)
- [Prompt Tuning without Labeled Samples for Zero-Shot Node Classification in Text-Attributed Graphs](https://mlsanity.com/paper/2601.03793/) (2026)

## Abstract (arXiv)

Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. However, the two tasks are challenging due to the lack of supervision signals, and existing methods only use the contrastive loss to align graph-based node embedding and language-based text embedding. In this paper, we propose Hound to improve accuracy by introducing more supervision signals, and the core idea is to go beyond the node-text pairs that come with data. Specifically, we design three augmentation techniques, i.e., node perturbation, text matching, and semantics negation to provide more reference nodes for each text and vice versa. Node perturbation adds/drops edges to produce diversified node embeddings that can be matched with a text. Text matching retrieves texts with similar embeddings to match with a node. Semantics negation uses a negative prompt to construct a negative text with the opposite semantics, which is contrasted with the original node and text. We evaluate Hound on 5 datasets and compare with 13 state-of-the-art baselines. The results show that Hound consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%.