TY - GEN
T1 - Generalized Few-Shot Node Classification
AU - Xu, Zhe
AU - Ding, Kaize
AU - Wang, Yu Xiong
AU - Liu, Huan
N1 - Funding Information: This work is supported by NSF (1947135, 2106825, and 2134079), the NSF Program on Fairness in AI in collaboration with Amazon (1939725), DARPA (HR001121C0165), NIFA (2020-67021-32799), ARO (W911NF2110088, W911NF2110030), ONR (N00014-21-1-4002), and ARL (W911NF2020124). The content of the information in this document does not necessarily reflect the position or the policy of the Government or Amazon, and no official endorsement should be inferred. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on. Publisher Copyright: © 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - For real-world graph data, the node class distribution is inherently imbalanced and long-tailed, which naturally leads to a few-shot learning scenario with limited nodes labeled for newly emerging classes. Existing efforts are carefully designed to solve such a few-shot learning problem via data augmentation, learning transferable initialization, to name a few. However, most, if not all, of them are based on a strong assumption that all the test nodes must exclusively come from novel classes, which is impractical in real-world applications. In this paper, we study a broader and more realistic problem named generalized few-shot node classification, where the test samples can be from both novel classes and base classes. Compared with the standard fewshot node classification, this new problem imposes several unique challenges, including asymmetric classification and inconsistent preference. To counter those challenges, we propose a shot-aware graph neural network (STAGER) equipped with an uncertainty-based weight assigner module for adaptive propagation. To formulate this problem from the meta-learning perspective, we propose a new training paradigm named imbalanced episodic training to ensure the label distribution is consistent between the training and test scenarios. Experiment results on four real-world datasets demonstrate the efficacy of our model, with up to 14% accuracy improvement over baselines.
AB - For real-world graph data, the node class distribution is inherently imbalanced and long-tailed, which naturally leads to a few-shot learning scenario with limited nodes labeled for newly emerging classes. Existing efforts are carefully designed to solve such a few-shot learning problem via data augmentation, learning transferable initialization, to name a few. However, most, if not all, of them are based on a strong assumption that all the test nodes must exclusively come from novel classes, which is impractical in real-world applications. In this paper, we study a broader and more realistic problem named generalized few-shot node classification, where the test samples can be from both novel classes and base classes. Compared with the standard fewshot node classification, this new problem imposes several unique challenges, including asymmetric classification and inconsistent preference. To counter those challenges, we propose a shot-aware graph neural network (STAGER) equipped with an uncertainty-based weight assigner module for adaptive propagation. To formulate this problem from the meta-learning perspective, we propose a new training paradigm named imbalanced episodic training to ensure the label distribution is consistent between the training and test scenarios. Experiment results on four real-world datasets demonstrate the efficacy of our model, with up to 14% accuracy improvement over baselines.
KW - graph mining
KW - meta-learning
KW - node classification
UR - http://www.scopus.com/inward/record.url?scp=85147734098&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147734098&partnerID=8YFLogxK
U2 - 10.1109/ICDM54844.2022.00071
DO - 10.1109/ICDM54844.2022.00071
M3 - Conference contribution
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 608
EP - 617
BT - Proceedings - 22nd IEEE International Conference on Data Mining, ICDM 2022
A2 - Zhu, Xingquan
A2 - Ranka, Sanjay
A2 - Thai, My T.
A2 - Washio, Takashi
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Conference on Data Mining, ICDM 2022
Y2 - 28 November 2022 through 1 December 2022
ER -