Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph

Liu, Zemin; Liu, Chenghao; Hoi, Steven C. H.

doi:10.1609/aaai.v35i5.16551

Cited by 50 publications

(26 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that other few-shot learning methods on graphs, such as Meta-GNN [57] and RALE [26], adopt a meta-learning paradigm [9]. Thus, they cannot be used in our setting, as they require labeled data in their base classes for the meta-training phase.…”

Section: Methodsmentioning

confidence: 99%

“…5.2. For task evaluation, as the 𝑘-shot tasks are balanced classification, we employ accuracy as the evaluation metric following earlier work [26,45].…”

Section: Methodsmentioning

confidence: 99%

“…We conduct this node-level task on three datasets, i.e., Flickr, PROTEINS, and ENZYMES. Following a typical 𝑘-shot setup [26,45,57], we generate a series of few-shot tasks for model training and validation. In particular, for PROTEINS and ENZYMES, on each graph we randomly generate ten 1-shot node classification tasks (i.e., in each task, we randomly sample 1 node per class) for training and validation, respectively.…”

Section: Performance Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Methodsmentioning

confidence: 99%

“…5.2. For task evaluation, as the 𝑘-shot tasks are balanced classification, we employ accuracy as the evaluation metric following earlier work [26,45].…”

Section: Methodsmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…Graph neural networks (GNNs) have shown outstanding performance in relational data representation learning [21], which has been extensively adopted in a number of applications, including node classification [22]- [24], link prediction [25]- [27], and anomaly detection [28]- [30]. Early efforts [31]- [33] usually utilize spectral GNNs based on the spectral graph theory, which begin with transferring graph signals into the embedding space, followed by spectral filters deduced from the graph Laplacian.…”

Section: Graph Neural Networkmentioning

confidence: 99%

Towards Semi-Supervised Universal Graph Classification

Luo

Zhao

Qin

et al. 2024

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Graph neural networks have pushed state-of-the-arts in graph classifications recently. Typically, these methods are studied within the context of supervised end-to-end training, which necessities copious task-specific labels. However, in real-world circumstances, labeled data could be limited, and there could be a massive corpus of unlabeled data, even from unknown classes as a complementary. Towards this end, we study the problem of semi-supervised universal graph classification, which not only identifies graph samples which do not belong to known classes, but also classifies the remaining samples into their respective classes. This problem is challenging due to a severe lack of labels and potential class shifts. In this paper, we propose a novel graph neural network framework named UGNN, which makes the best of unlabeled data from the subgraph perspective. To tackle class shifts, we estimate the certainty of unlabeled graphs using multiple subgraphs, which facilities the discovery of unlabeled data from unknown categories. Moreover, we construct semantic prototypes in the embedding space for both known and unknown categories and utilize posterior prototype assignments inferred from the Sinkhorn-Knopp algorithm to learn from abundant unlabeled graphs across different subgraph views. Extensive experiments on six datasets verify the effectiveness of UGNN in different settings.

show abstract

“…The method only uses the graph structure to obtain latent representations of task nodes. A recent study by Liu et al [16] pointed out that it is vital to learn the dependencies between nodes in the classification task. Thus, they assigned each node to relative positions to get node-level dependencies.…”

Section: Introductionmentioning

confidence: 99%

Graph Relation Networks for Few-shot Node Classification on Attributed Networks

里

刘

张

2023

Preprint

View full text Add to dashboard Cite

Few-shot learning has been solving classification problems with few labels in the image and text domains, which has achieved great success in such Euclidean domains. However, a large amount of data can be represented as attributed networks defined by non-Euclidean domains, and fewer studies have successfully applied few-shot learning to attributed networks. Firstly, they ignore the relationship between nodes, so they can not obtain an adequate and accurate representation of nodes. Secondly, the use of an artificial set distance function to measure the similarity between nodes is defective. Because some special samples can cause perturbation to the classifier. In order to solve the above problems, we propose a new framework based on relation networks - graph relation networks (GRN). Specifically, GRN first sets up an episode training mechanism to simulate a real-world few-shot scenario, then uses graph attention networks to obtain a representation of each node with importance scores, and finally learns to compare the similarity of unclassified and classified nodes through the relation network. We conduct extensive experiments on real-world datasets. The experimental results show that the method improves the performance of graph node classification.

show abstract

Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph

Cited by 50 publications

References 31 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

Towards Semi-Supervised Universal Graph Classification

Graph Relation Networks for Few-shot Node Classification on Attributed Networks

Contact Info

Product

Resources

About