ABSTRACT
Graph few-shot learning aims to learn how to quickly adapt to new tasks using only a few labeled data, which transfers learned knowledge of base classes to novel classes. Existing methods are mainly designed for static graphs, while many real-world graphs are dynamic and evolving over time, resulting in a phenomenon of structure and class evolutions. To address the challenges caused by the phenomenon, in this paper, we propose a novel algorithm named Learning to Generate Parameters (LGP) to deal with few-shot class-evolutionary learning on dynamic graphs. Specifically, for the structure evolution, LGP integrates ensemble learning into a backbone network to effectively learn invariant representation across different snapshots within a dynamic graph. For the class evolution, LGP adopts a meta-learning strategy that can learn to generate the classified parameters of novel classes via the parameters of the base classes. Therefore, LGP can quickly adapt to new tasks on a combination of base and novel classes. Besides, LGP utilizes an attention mechanism to capture the evolutionary pattern between the novel and based classes. Extensive experiments on a real-world dataset demonstrate the effectiveness of LGP.
- Avishek Joey Bose, Ankit Jain, Piero Molino, and William L. Hamilton. 2019. Meta-Graph: Few Shot Link Prediction via Meta Learning. In NeurIPS.Google Scholar
- Wei-Lun Chao, Soravit Changpinyo, Boqing Gong, and Fei Sha. 2016. An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In ECCV.Google Scholar
- Zhengyu Chen and Donglin Wang. 2021. Multi-Initialization Meta-Learning with Domain Adaptation. In ICASSP.Google Scholar
- Eli Chien, Jianhao Peng, Pan Li, and Olgica Milenkovic. 2021. Adaptive Universal Generalized PageRank Graph Neural Network. In ICLR.Google Scholar
- Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. In ICML.Google Scholar
- Spyros Gidaris and Nikos Komodakis. 2018. Dynamic Few-shot Visual Learning without Forgetting. In CVPR.Google Scholar
- Palash Goyal, Nitin Kamra, Xinran He, and Yan Liu. 2018. DynGEM: Deep Embedding Method for Dynamic Graphs. In IJCAI.Google Scholar
- Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. In NeurIPS.Google Scholar
- Kexin Huang and Marinka Zitnik. 2020. Graph Meta Learning via Local Subgraphs. In NeurIPS.Google Scholar
- Thomas N Kipf and Max Welling. 2017. Semi-supervised Classification with Graph Convolutional Networks. In ICLR.Google Scholar
- Lin Lan, Pinghui Wang, Xuefeng Du, Kaikai Song, Jing Tao, and Xiaohong Guan. 2020. Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding. In NeurIPS.Google Scholar
- Zemin Liu, Yuan Fang, Chenghao Liu, and Steven CH Hoi. 2021. Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph. In AAAI.Google Scholar
- Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, and Charles E. Leiserson. 2020. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In AAAI.Google Scholar
- Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. 2019. Dynamic Graph Representation Learning via Self-Attention Networks. In ICLR.Google Scholar
- Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling Relational Data with Graph Convolutional Networks. In ESWC.Google Scholar
- Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical Networks for Few-shot Learning. In NeurIPS.Google Scholar
- Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. 2019. Dyrep: Learning Representations over Dynamic Graphs. In ICLR.Google Scholar
- Cornell University. 1998. Computer Science Subject Areas and Moderators. https://arxiv.org/corr/subjectclasses.Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In NeurIPS.Google Scholar
- Yaqing Wang, Quanming Yao, James Tin Yau Kwok, and Lionel Ming-Shuan Ni. 2020. Generalizing from a Few Examples: A survey on Few-shot Learning. Comput. Surveys (2020).Google Scholar
- Felix Wu, Amauri Souza, Tianyi Zhang, Christopher Fifty, Tao Yu, and Kilian Weinberger. 2019. Simplifying Graph Convolutional Networks. In ICML.Google Scholar
- Qitian Wu, Hengrui Zhang, Junchi Yan, and David Wipf. 2022. Handling Distribution Shifts on Graphs: An Invariance Perspective. In ICLR.Google Scholar
- Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. 2020. A Comprehensive Survey on Graph Neural Networks. TNNLS (2020).Google Scholar
- Teng Xiao, Zhengyu Chen, Donglin Wang, and Suhang Wang. 2021. Learning How to Propagate Messages in Graph Neural Networks. In KDD.Google Scholar
- Cheng Yang, Chunchen Wang, Yuanfu Lu, Xumeng Gong, Chuan Shi, Wei Wang, and Xu Zhang. 2022. Few-shot Link Prediction in Dynamic Networks. In WSDM.Google Scholar
- Hao Yuan, Haiyang Yu, Shurui Gui, and Shuiwang Ji. 2020. Explainability in Graph Neural Networks: A Taxonomic Survey. In CoRR.Google Scholar
- Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, and Jun Gao. 2017. Scalable graph embedding for asymmetric proximity. In AAAI.Google Scholar
- Fan Zhou, Chengtai Cao, Kunpeng Zhang, Goce Trajcevski, Ting Zhong, and Ji Geng. 2019. Meta-GNN: On Few-shot Node Classification in Graph Meta-learning. In CIKM.Google Scholar
Index Terms
- LGP: Few-Shot Class-Evolutionary Learning on Dynamic Graphs
Recommendations
ROLAND: Graph Learning Framework for Dynamic Graphs
KDD '22: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data MiningGraph Neural Networks (GNNs) have been successfully applied to many real-world static graphs. However, the success of static graphs has not fully translated to dynamic graphs due to the limitations in model design, evaluation settings, and training ...
Self-supervised Representation Learning on Dynamic Graphs
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementGraph representation learning has now become the de facto standard when dealing with graph-structured data. Using powerful tools from deep learning and graph neural networks, recent works have applied graph representation learning to time-evolving ...
Robust Graph Meta-Learning for Weakly Supervised Few-Shot Node Classification
Graph machine learning (Graph ML) models typically require abundant labeled instances to provide sufficient supervision signals, which is commonly infeasible in real-world scenarios since labeled data for newly emerged concepts (e.g., new categorizations ...
Comments