TY - GEN
T1 - Virtual Node Tuning for Few-shot Node Classification
AU - Tan, Zhen
AU - Guo, Ruocheng
AU - Ding, Kaize
AU - Liu, Huan
N1 - Publisher Copyright: © 2023 ACM.
PY - 2023/8/6
Y1 - 2023/8/6
N2 - Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge from base classes with abundant labels to target novel classes. However, existing solutions become ineffective or inapplicable when base classes have no or limited labeled nodes. To address this challenge, we propose an innovative method dubbed Virtual Node Tuning (VNT). Our approach utilizes a pretrained graph transformer as the encoder and injects virtual nodes as soft prompts in the embedding space, which can be optimized with few-shot labels in novel classes to modulate node embeddings for each specific FSNC task. A unique feature of VNT is that, by incorporating a Graph-based Pseudo Prompt Evolution (GPPE) module, VNT-GPPE can handle scenarios with sparse labels in base classes. Experimental results on four datasets demonstrate the superiority of the proposed approach in addressing FSNC with unlabeled or sparsely labeled base classes, outperforming existing state-of-the-art methods and even fully supervised baselines.
AB - Few-shot Node Classification (FSNC) is a challenge in graph representation learning where only a few labeled nodes per class are available for training. To tackle this issue, meta-learning has been proposed to transfer structural knowledge from base classes with abundant labels to target novel classes. However, existing solutions become ineffective or inapplicable when base classes have no or limited labeled nodes. To address this challenge, we propose an innovative method dubbed Virtual Node Tuning (VNT). Our approach utilizes a pretrained graph transformer as the encoder and injects virtual nodes as soft prompts in the embedding space, which can be optimized with few-shot labels in novel classes to modulate node embeddings for each specific FSNC task. A unique feature of VNT is that, by incorporating a Graph-based Pseudo Prompt Evolution (GPPE) module, VNT-GPPE can handle scenarios with sparse labels in base classes. Experimental results on four datasets demonstrate the superiority of the proposed approach in addressing FSNC with unlabeled or sparsely labeled base classes, outperforming existing state-of-the-art methods and even fully supervised baselines.
KW - few-shot learning
KW - graph neural networks
KW - prompt
UR - http://www.scopus.com/inward/record.url?scp=85171369945&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85171369945&partnerID=8YFLogxK
U2 - 10.1145/3580305.3599541
DO - 10.1145/3580305.3599541
M3 - Conference contribution
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 2177
EP - 2188
BT - KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
T2 - 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Y2 - 6 August 2023 through 10 August 2023
ER -