Few-Shot Learning on Graphs: A Survey

Graph representation learning has attracted tremendous attention due to its remarkable performance in many real-world applications. However, prevailing supervised graph representation learning models for specific tasks often suffer from label sparsity issue as data labeling is always time and resource consuming. In light of this, few-shot learning on graphs (FSLG), which combines the strengths of graph representation learning and few-shot learning together, has been proposed to tackle the performance degradation in face of limited annotated data challenge. There have been many studies working on FSLG recently. In this paper, we comprehensively survey these work in the form of a series of methods and applications. Specifically, we first introduce FSLG challenges and bases, then categorize and summarize existing work of FSLG in terms of three major graph mining tasks at different granularity levels, i.e., node, edge, and graph. Finally, we share our thoughts on some future research directions of FSLG. The authors of this survey have contributed significantly to the AI literature on FSLG over the last few years.

[1]  Kaveh Hassani,et al.  Cross-Domain Few-Shot Graph Classification , 2022, AAAI.

[2]  Ruocheng Guo,et al.  Graph Few-shot Class-incremental Learning , 2021, Web Search and Data Mining.

[3]  Huan Liu,et al.  Meta Propagation Networks for Graph Few-shot Semi-supervised Learning , 2021, AAAI.

[4]  Timothy M. Hospedales,et al.  Meta-Learning in Neural Networks: A Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Wenwu Zhu,et al.  Deep Learning on Graphs: A Survey , 2018, IEEE Transactions on Knowledge and Data Engineering.

[6]  Yiming Zhang,et al.  Adapting Distilled Knowledge for Few-shot Relation Reasoning over Knowledge Graphs , 2022, SDM.

[7]  Xiangliang Zhang,et al.  HG-Meta: Graph Meta-learning over Heterogeneous Graphs , 2022, SDM.

[8]  Liang Wu,et al.  REFORM: Error-Aware Few-Shot Knowledge Graph Completion , 2021, CIKM.

[9]  Zifeng Zhuang,et al.  HINFShot: A Challenge Dataset for Few-Shot Node Classification in Heterogeneous Information Network , 2021, ICMR.

[10]  Feng Zhao,et al.  Multi-Initialization Graph Meta-Learning for Node Classification , 2021, ICMR.

[11]  Yuan Fang,et al.  Tail-GNN: Tail-Node Graph Neural Networks , 2021, KDD.

[12]  Yiyue Qian,et al.  Adapting Meta Knowledge with Heterogeneous Information Network for COVID-19 Themed Malicious Repository Detection , 2021, IJCAI.

[13]  Abulikemu Abuduweili,et al.  Property-Aware Relation Networks for Few-Shot Molecular Property Prediction , 2021, NeurIPS.

[14]  Jianliang Gao,et al.  MetaP: Meta Pattern Learning for One-Shot Knowledge Graph Completion , 2021, SIGIR.

[15]  Steven C. H. Hoi,et al.  Relative and Absolute Location Embedding for Few-Shot Node Classification on Graph , 2021, AAAI.

[16]  Guanglin Niu,et al.  Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion , 2021, SIGIR.

[17]  B. Uzzi,et al.  Meta-Learning with Graph Neural Networks: Methods and Applications , 2021, ArXiv.

[18]  Hanghang Tong,et al.  Few-shot Network Anomaly Detection via Cross-network Meta-learning , 2021, WWW.

[19]  Nitesh V. Chawla,et al.  Few-Shot Graph Learning for Molecular Property Prediction , 2021, WWW.

[20]  Joelle Pineau,et al.  Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs , 2021, EACL.

[21]  Mohammad Rostami,et al.  One-shot Learning for Temporal Knowledge Graphs , 2020, AKBC.

[22]  Michael I. Jordan,et al.  Provable Meta-Learning of Linear Representations , 2020, ICML.

[23]  S. Kakade,et al.  Few-Shot Learning via Learning the Representation, Provably , 2020, ICLR.

[24]  Yanfang Ye,et al.  Distilling Meta Knowledge on Heterogeneous Graph for Illicit Drug Trafficker Detection on Social Media , 2021, NeurIPS.

[25]  Cuiping Li,et al.  P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion , 2021, EMNLP.

[26]  Nitesh Chawla,et al.  Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases , 2020, FINDINGS.

[27]  Zhangyang Wang,et al.  Graph Contrastive Learning with Augmentations , 2020, NeurIPS.

[28]  Qinghua Zheng,et al.  Graph Few-shot Learning with Attribute Matching , 2020, CIKM.

[29]  Hongbo Xu,et al.  Adaptive Attentional Network for Few-Shot Knowledge Graph Completion , 2020, EMNLP.

[30]  Enhong Chen,et al.  ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Prediction , 2020, KDD.

[31]  Chuan Shi,et al.  Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation , 2020, KDD.

[32]  X. Guan,et al.  Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding , 2020, NeurIPS.

[33]  Huan Liu,et al.  Graph Prototypical Networks for Few-shot Learning on Attributed Networks , 2020, CIKM.

[34]  Marinka Zitnik,et al.  Graph Meta Learning via Local Subgraphs , 2020, NeurIPS.

[35]  Sung Ju Hwang,et al.  Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction , 2020, NeurIPS.

[36]  Xifeng Yan,et al.  Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification , 2020, CIKM.

[37]  Manohar Kaul,et al.  Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures , 2020, ICLR.

[38]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[39]  Chunyun Zhang,et al.  Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs , 2020, AAAI.

[40]  Nitesh V. Chawla,et al.  Few-Shot Knowledge Graph Completion , 2019, AAAI.

[41]  Junzhou Huang,et al.  Graph Few-shot Learning via Knowledge Transfer , 2019, AAAI.

[42]  S. Fidler,et al.  A Theoretical Analysis of the Number of Shots in Few-Shot Learning , 2019, ICLR.

[43]  William L. Hamilton,et al.  Meta-Graph: Few shot Link Prediction via Meta Learning , 2019, ArXiv.

[44]  Xin Lv,et al.  Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations , 2019, EMNLP.

[45]  Nitesh V. Chawla,et al.  Heterogeneous Graph Neural Network , 2019, KDD.

[46]  Yizhou Sun,et al.  Few-Shot Representation Learning for Out-Of-Vocabulary Words , 2019, ACL.

[47]  Quanshi Zhang,et al.  Towards a Deep and Unified Understanding of Deep Neural Models in NLP , 2019, ICML.

[48]  Ji Geng,et al.  Meta-GNN: On Few-shot Node Classification in Graph Meta-learning , 2019, CIKM.

[49]  James T. Kwok,et al.  Generalizing from a Few Examples , 2019, ACM Comput. Surv..

[50]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

[51]  Qiang Chen,et al.  Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs , 2019, EMNLP-IJCNLP 2019.

[52]  Mo Yu,et al.  One-Shot Relational Learning for Knowledge Graphs , 2018, EMNLP.

[53]  Jure Leskovec,et al.  Hierarchical Graph Representation Learning with Differentiable Pooling , 2018, NeurIPS.

[54]  Sergey Levine,et al.  Probabilistic Model-Agnostic Meta-Learning , 2018, NeurIPS.

[55]  Jure Leskovec,et al.  Graph Convolutional Neural Networks for Web-Scale Recommender Systems , 2018, KDD.

[56]  Yu Cheng,et al.  Diverse Few-Shot Text Classification with Multiple Metrics , 2018, NAACL.

[57]  Tao Xiang,et al.  Learning to Compare: Relation Network for Few-Shot Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[58]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[59]  Pasquale Minervini,et al.  Convolutional 2D Knowledge Graph Embeddings , 2017, AAAI.

[60]  Regina Barzilay,et al.  Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network , 2017, NIPS.

[61]  Nitesh V. Chawla,et al.  metapath2vec: Scalable Representation Learning for Heterogeneous Networks , 2017, KDD.

[62]  Marcin Andrychowicz,et al.  One-Shot Imitation Learning , 2017, NIPS.

[63]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[64]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[65]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[66]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[67]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[68]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[69]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[70]  Danqi Chen,et al.  Reasoning With Neural Tensor Networks for Knowledge Base Completion , 2013, NIPS.

[71]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.