Robust Graph Meta-Learning for Weakly Supervised Few-Shot Node Classification
Article No.: 83, Pages 1 - 18
Abstract
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 of nodes) on graphs is rather limited. To efficiently learn with a small amount of data on graphs, meta-learning has been investigated in Graph ML. By transferring the knowledge learned from previous experiences to new tasks, graph meta-learning approaches have demonstrated promising performance on few-shot graph learning problems. However, most existing efforts predominately assume that all the data from the seen classes is gold labeled, yet those methods may lose their efficacy when the seen data is weakly labeled with severe label noise. As such, we aim to investigate a novel problem of weakly supervised graph meta-learning for improving the model robustness in terms of knowledge transfer. To achieve this goal, we propose Meta-GIN (Meta Graph Interpolation Network), a new graph meta-learning framework. Based on a new robustness-enhanced episodic training paradigm, Meta-GIN is meta-learned to interpolate node representations from weakly labeled data and extracts highly transferable meta-knowledge, which enables the model to quickly adapt to unseen tasks with few labeled instances. Extensive experiments demonstrate the superiority of Meta-GIN over existing graph meta-learning studies on the task of weakly supervised few-shot node classification.
References
[1]
Jinheon Baek, Dong Bok Lee, and Sung Ju Hwang. 2020. Learning to extrapolate knowledge: Transductive few-shot out-of-graph link prediction. In Proceedings ofNeurIPS.
[2]
Jatin Chauhan, Deepak Nathani, and Manohar Kaul. 2019. Few-shot learning on graphs via super-classes based on graph spectral measures. In Proceedings of ICLR.
[3]
Pengfei Chen, Ben Ben Liao, Guangyong Chen, and Shengyu Zhang. 2019. Understanding and utilizing deep neural networks trained with noisy labels. In Proceedings of ICML.
[4]
Kaize Ding, Jundong Li, Rohit Bhanushali, and Huan Liu. 2019. Deep anomaly detection on attributed networks. In Proceedings of SDM.
[5]
Kaize Ding, Jianling Wang, Jundong Li, Kai Shu, Chenghao Liu, and Huan Liu. 2020. Graph prototypical networks for few-shot learning on attributed networks. In Proceedings of CIKM.
[6]
Kaize Ding, Zhe Xu, Hanghang Tong, and Huan Liu. 2022. Data augmentation for deep graph learning: A survey. ACM SIGKDD Explorations Newsletter 24, 2 (2022), 61–77.
[7]
Hande Dong, Jiawei Chen, Fuli Feng, Xiangnan He, Shuxian Bi, Zhaolin Ding, and Peng Cui. 2021. On the equivalence of decoupled graph convolution network and label propagation. In Proceedings of WWW.
[8]
Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of ICML.
[9]
Zheng Gao, Hongsong Li, Zhuoren Jiang, and Xiaozhong Liu. 2020. Detecting user community in sparse domain via cross-graph pairwise learning. In Proceedings of SIGIR.
[10]
Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of KDD.
[11]
Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Proceedings of NeurIPS.
[12]
Xiaorong Hao, Tao Lian, and Li Wang. 2020. Dynamic link prediction by integrating node vector evolution and local neighborhood representation. In Proceedings of SIGIR.
[13]
Xiangnan He, Kuan Deng, Xiang Wang, Yan Li, Yongdong Zhang, and Meng Wang. 2020. LightGCN: Simplifying and powering graph convolution network for recommendation. In Proceedings of SIGIR.
[14]
Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. 2018. Using trusted data to train deep networks on labels corrupted by severe noise. In Proceedings of NeurIPS.
[15]
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 Proceedings of NeurIPS.
[16]
Kexin Huang and Marinka Zitnik. 2020. Graph meta learning via local subgraphs. In Proceedings of NeurIPS.
[17]
Lu Jiang, Zhengyuan Zhou, Thomas Leung, Li-Jia Li, and Li Fei-Fei. 2018. MentorNet: Learning data-driven curriculum for very deep neural networks on corrupted labels. In Proceedings of ICML.
[18]
Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of NeurIPS.
[19]
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 Proceedings of NeurIPS.
[20]
Feng Li, Zhenrui Chen, Pengjie Wang, Yi Ren, Di Zhang, and Xiaoyu Zhu. 2019. Graph intention network for click-through rate prediction in sponsored search. In Proceedings of SIGIR.
[21]
Zhenguo Li, Fengwei Zhou, Fei Chen, and Hang Li. 2017. Meta-SGD: Learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835 (2017).
[22]
Jianghao Lin, Weiwen Liu, Xinyi Dai, Weinan Zhang, Shuai Li, Ruiming Tang, Xiuqiang He, Jianye Hao, and Yong Yu. 2021. A graph-enhanced click model for web search. In Proceedings of SIGIR. 1259–1268.
[23]
Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, and Chengqi Zhang. 2019. Learning to propagate for graph meta-learning. In Proceedings of NeurIPS.
[24]
Yonghao Liu, Mengyu Li, Ximing Li, Fausto Giunchiglia, Xiaoyue Feng, and Renchu Guan. 2022. Few-shot node classification on attributed networks with graph meta-learning. In Proceedings of SIGIR.
[25]
Zemin Liu, Yuan Fang, Chenghao Liu, and Steven C. H. Hoi. 2021. Relative and absolute location embedding for few-shot node classification on graph. In Proceedings of AAAI.
[26]
Zemin Liu, Wentao Zhang, Yuan Fang, Xinming Zhang, and Steven C. H. Hoi. 2020. Towards locality-aware meta-learning of tail node embeddings on networks. In Proceedings of CIKM.
[27]
Ning Ma, Jiajun Bu, Jieyu Yang, Zhen Zhang, Chengwei Yao, Zhi Yu, Sheng Zhou, and Xifeng Yan. 2020. Adaptive-step graph meta-learner for few-shot graph classification. In Proceedings of CIKM.
[28]
Julian McAuley, Rahul Pandey, and Jure Leskovec. 2015. Inferring networks of substitutable and complementary products. In Proceedings of KDD.
[29]
Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. 2018. A simple neural attentive meta-learner. In Proceedings of ICLR.
[30]
Wentao Ouyang, Xiuwu Zhang, Shukui Ren, Li Li, Kun Zhang, Jinmei Luo, Zhaojie Liu, and Yanlong Du. 2021. Learning graph meta embeddings for cold-start ads in click-through rate prediction. In Proceedings of SIGIR.
[31]
Guo-Jun Qi, Charu Aggarwal, Qi Tian, Heng Ji, and Thomas Huang. 2012. Exploring context and content links in social media: A latent space method. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 5 (2012), 850–862.
[32]
Sachin Ravi and Hugo Larochelle. 2017. Optimization as a model for few-shot learning. In Proceedings of ICLR.
[33]
Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, and Richard S. Zemel. 2018. Meta-learning for semi-supervised few-shot classification. In Proceedings of ICLR.
[34]
Mengye Ren, Wenyuan Zeng, Bin Yang, and Raquel Urtasun. 2018. Learning to reweight examples for robust deep learning. In Proceedings of ICML.
[35]
Adam Santoro, Sergey Bartunov, Matthew Botvinick, Daan Wierstra, and Timothy Lillicrap. 2016. Meta-learning with memory-augmented neural networks. In Proceedings of ICML.
[36]
Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Proceedings of NeurIPS.
[37]
Flood Sung, Yongxin Yang, Li Zhang, Tao Xiang, Philip H. S. Torr, and Timothy M. Hospedales. 2018. Learning to compare: Relation network for few-shot learning. In Proceedings of CVPR.
[38]
Jie Tang, Jing Zhang, Limin Yao, Juanzi Li, Li Zhang, and Zhong Su. 2008. ArnetMiner: Extraction and mining of academic social networks. In Proceedings of KDD.
[39]
Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In Proceedings of ICLR.
[40]
Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, and Daan Wierstra. 2016. Matching networks for one shot learning. In Proceedings of NeurIPS.
[41]
Jianling Wang, Kaize Ding, Liangjie Hong, Huan Liu, and James Caverlee. 2020. Next-item recommendation with sequential hypergraphs. In Proceedings of SIGIR.
[42]
Ning Wang, Minnan Luo, Kaize Ding, Lingling Zhang, Jundong Li, and Qinghua Zheng. 2020. Graph few-shot learning with attribute matching. In Proceedings of CIKM.
[43]
Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. In Proceedings of TKDE.
[44]
Song Wang, Kaize Ding, Chuxu Zhang, Chen Chen, and Jundong Li. 2022. Task-adaptive few-shot node classification. In Proceedings of KDD.
[45]
Zhihao Wen, Yuan Fang, and Zemin Liu. 2021. Meta-inductive node classification across graphs. In Proceedings of SIGIR.
[46]
Felix Wu, Tianyi Zhang, Amauri Holanda de Souza Jr., Christopher Fifty, Tao Yu, and Kilian Q. Weinberger. 2019. Simplifying graph convolutional networks. In Proceedings of ICML.
[47]
Huaxiu Yao, Chuxu Zhang, Ying Wei, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, and Zhenhui Li. 2020. Graph few-shot learning via knowledge transfer. In Proceedings of AAAI.
[48]
Chuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, and Nitesh V. Chawla. 2020. Few-shot knowledge graph completion. In Proceedings of AAAI.
[49]
Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, and Xiaokang Yang. 2019. Variational few-shot learning. In Proceedings of ICCV.
[50]
Shichao Zhang and Jiaye Li. 2023. KNN classification with one-step computation. IEEE Transactions on Knowledge and Data Engineering 35, 3 (2023), 2711–2723.
[51]
Shichao Zhang, Jiaye Li, and Yangding Li. 2023. Reachable distance function for KNN classification. IEEE Transaction on Knowledge and Data Engineering 35 (2023), 7382–7396.
[52]
Tiantian Zhang and Bin Wu. 2012. A method for local community detection by finding core nodes. In Proceedings of ASONAM.
[53]
Weihe Zhang, Yali Wang, and Yu Qiao. 2019. MetaCleaner: Learning to hallucinate clean representations for noisy-labeled visual recognition. In Proceedings of CVPR.
[54]
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 Proceedings of CIKM.
[55]
Linchao Zhu and Yi Yang. 2018. Compound memory networks for few-shot video classification. In Proceedings of ECCV.
Index Terms
- Robust Graph Meta-Learning for Weakly Supervised Few-Shot Node Classification
Recommendations
Few-shot Node Classification with Extremely Weak Supervision
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningFew-shot node classification aims at classifying nodes with limited labeled nodes as references. Recent few-shot node classification methods typically learn from classes with abundant labeled nodes (i.e., meta-training classes) and then generalize to ...
Contrastive Meta-Learning for Few-shot Node Classification
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningFew-shot node classification, which aims to predict labels for nodes on graphs with only limited labeled nodes as references, is of great significance in real-world graph mining tasks. To tackle such a label shortage issue, existing works generally ...
Semantic guide for semi-supervised few-shot multi-label node classification
AbstractWe study a new research problem named semi-supervised few-shot multi-label node classification which has the following characteristics: 1) the extreme imbalance between the number of labeled and unlabeled nodes that are connected on ...
Comments
Information & Contributors
Information
Published In
May 2024
707 pages
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 13 February 2024
Online AM: 10 November 2023
Accepted: 26 September 2023
Revised: 03 August 2023
Received: 23 April 2023
Published in TKDD Volume 18, Issue 4
Check for updates
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 232Total Downloads
- Downloads (Last 12 months)232
- Downloads (Last 6 weeks)31
Reflects downloads up to 10 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in