Towards Efficient Temporal Graph Learning: Algorithms, Frameworks, and Tools
Pages 5530 - 5533
Abstract
Temporal graphs capture dynamic node relations via temporal edges, finding extensive utility in wide domains where time-varying patterns are crucial. Temporal Graph Neural Networks (TGNNs) have gained significant attention for their effectiveness in representing temporal graphs. However, TGNNs still face significant efficiency challenges in real-world low-resource settings. First, from a data-efficiency standpoint, training TGNNs requires sufficient temporal edges and data labels, which is problematic in practical scenarios with limited data collection and annotation. Second, from a resource-efficiency perspective, TGNN training and inference are computationally demanding due to complex encoding operations, especially on large-scale temporal graphs. Minimizing resource consumption while preserving effectiveness is essential. Inspired by these efficiency challenges, this tutorial systematically introduces state-of-the-art data-efficient and resource-efficient TGNNs, focusing on algorithms, frameworks, and tools, and discusses promising yet under-explored research directions in efficient temporal graph learning. This tutorial aims to benefit researchers and practitioners in data mining, machine learning, and artificial intelligence.
References
[1]
Mohammad Alomrani, Mahdi Biparva, Yingxue Zhang, and Mark Coates. Dyg2vec: Efficient representation learning for dynamic graphs. TMLR '24, 2024.
[2]
Ke-Jia Chen, Linsong Liu, Linpu Jiang, and Jingqiang Chen. Self-supervised dynamic graph representation learning via temporal subgraph contrast. ACM Trans. Knowl. Discov. Data, 2023.
[3]
Weilin Cong, Si Zhang, Jian Kang, Baichuan Yuan, Hao Wu, Xin Zhou, Hanghang Tong, and Mehrdad Mahdavi. Do we really need complicated model architectures for temporal networks? In ICLR '23, 2023.
[4]
Matthias Fey and Jan E. Lenssen. Fast graph representation learning with PyTorch Geometric. In WICLR on Graphs and Manifolds, 2019.
[5]
Kaihua Fu, Quan Chen, Yuzhuo Yang, Jiuchen Shi, Chao Li, and Minyi Guo. Blad: Adaptive load balanced scheduling and operator overlap pipeline for accelerating the dynamic gnn training. In SC '23, 2023.
[6]
Shihong Gao, Yiming Li, Yanyan Shen, Yingxia Shao, and Lei Chen. Etc: Efficient training of temporal graph neural networks over large-scale dynamic graphs. In VLDB '24, 2024.
[7]
Shihong Gao, Yiming Li, Xin Zhang, Yanyan Shen, Yingxia Shao, and Lei Chen. Simple: Efficient temporal graph neural network training at scale with dynamic data placement. In SIGMOD '24, 2024.
[8]
Mingyu Guan, Anand Padmanabha Iyer, and Taesoo Kim. Dynagraph: Dynamic graph neural networks at scale. In GRADES-NDA '22, 2022.
[9]
Ehsan Hajiramezanali, Arman Hasanzadeh, Krishna Narayanan, Nick Duffield, Mingyuan Zhou, and Xiaoning Qian. Variational graph recurrent neural networks. In NeurIPS '19, 2019.
[10]
Shenyang Huang, Farimah Poursafaei, Jacob Danovitch, Matthias Fey, Weihua Hu, Emanuele Rossi, Jure Leskovec, Michael Bronstein, Guillaume Rabusseau, and Reihaneh Rabbany. Temporal graph benchmark for machine learning on temporal graphs. In NeurIPS '23, 2023.
[11]
Tiancheng Huang, Feng Zhao, and Donglin Wang. Lgp: Few-shot class-evolutionary learning on dynamic graphs. In CIKM '22, 2022.
[12]
Lingwen Liu, Guangqi Wen, Peng Cao, Jinzhu Yang, Weiping Li, and Osmar R. Zaiane. Capturing temporal node evolution via self-supervised learning: A new perspective on dynamic graph learning. In WSDM '24, 2024.
[13]
Linhao Luo, Gholamreza Haffari, and Shirui Pan. Graph sequential neural ode process for link prediction on dynamic and sparse graphs. In WSDM '23, 2023.
[14]
Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. Temporal graph networks for deep learning on dynamic graphs. In ICML 2020 Workshop on Graph Representation Learning, 2020.
[15]
Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. In WSDM '20, 2020.
[16]
Sheng Tian, Ruofan Wu, Leilei Shi, Liang Zhu, and Tao Xiong. Self-supervised representation learning on dynamic graphs. In CIKM '21, 2021.
[17]
Minjie Wang, Da Zheng, Zihao Ye, Quan Gan, Mufei Li, Xiang Song, Jinjing Zhou, Chao Ma, Lingfan Yu, Yu Gai, Tianjun Xiao, Tong He, George Karypis, Jinyang Li, and Zheng Zhang. Deep graph library: A graph-centric, highly-performant package for graph neural networks. CoRR, 2019.
[18]
Ruijie Wang, Jingyuan Huang, Yutong Zhang, Jinyang Li, Yufeng Wang, Wanyu Zhao, Shengzhong Liu, Charith Mendis, and Tarek Abdelzaher. Tgonline: Enhancing temporal graph learning with adaptive online meta-learning. In SIGIR '24, 2024.
[19]
Ruijie Wang, Zheng Li, Jingfeng Yang, Tianyu Cao, Chao Zhang, Bing Yin, and Tarek Abdelzaher. Mutually-paced knowledge distillation for cross-lingual temporal knowledge graph reasoning. In The Web Conference, 2023.
[20]
Ruijie Wang, Yutong Zhang, Jinyang Li, Shengzhong Liu, Dachun Sun, Tianchen Wang, Tianshi Wang, Yizhuo Chen, Denizhan Kara, and Tarek Abdelzaher. Metahkg: Meta hyperbolic learning for few-shot temporal reasoning. In SIGIR '24, 2024.
[21]
Ruijie Wang, zheng li, Dachun Sun, Shengzhong Liu, Jinning Li, Bing Yin, and Tarek Abdelzaher. Learning to sample and aggregate: Few-shot reasoning over temporal knowledge graphs. In NeurIPS '22, 2022.
[22]
Yufeng Wang and Charith Mendis. Tgopt: Redundancy-aware optimizations for temporal graph attention networks. In PPoPP '23, 2023.
[23]
Yufeng Wang and Charith Mendis. Tglite: A lightweight programming framework for continuous-time temporal graph neural networks. In ASPLOS '24, 2024.
[24]
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. Inductive representation learning on temporal graphs. In ICLR '20, 2020.
[25]
Cheng Yang, Chunchen Wang, Yuanfu Lu, Xumeng Gong, Chuan Shi, Wei Wang, and Xu Zhang. Few-shot link prediction in dynamic networks. In WSDM '22.
[26]
Xingtong Yu, Yuan Fang, Zemin Liu, Yuxia Wu, Zhihao Wen, Jianyuan Bo, Xinming Zhang, and Steven C. H. Hoi. Few-shot learning on graphs: from meta-learning to pre-training and prompting. CoRR, 2024.
[27]
Guolin Zhang, Zehui Hu, Guoqiu Wen, Junbo Ma, and Xiaofeng Zhu. Dynamic graph convolutional networks by semi-supervised contrastive learning. Pattern Recogn., 2023.
[28]
Hongkuan Zhou, Da Zheng, Israt Nisa, Vassilis N. Ioannidis, Xiang Song, and George Karypis. TGL: A general framework for temporal GNN training on billion-scale graphs. In VLDB '22, 2022.
[29]
Hongkuan Zhou, Da Zheng, Xiang Song, George Karypis, and Viktor Prasanna. Disttgl: Distributed memory-based temporal graph neural network training. In SC '23, 2023.
Index Terms
- Towards Efficient Temporal Graph Learning: Algorithms, Frameworks, and Tools
Recommendations
Time-aware Graph Structure Learning via Sequence Prediction on Temporal Graphs
CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge ManagementTemporal Graph Learning, which aims to model the time-evolving nature of graphs, has gained increasing attention and achieved remarkable performance recently. However, in reality, graph structures are often incomplete and noisy, which hinders temporal ...
Mengerian Temporal Graphs Revisited
Fundamentals of Computation TheoryAbstractA temporal graph is a graph that changes with time. More specifically, it is a pair where G is a graph and is a function on the edges of G that describes when each edge is active. Given vertices , a temporal -path is a ...
A new temporal interpretation of cluster editing
AbstractThe NP-complete graph problem Cluster Editing seeks to transform a static graph into a disjoint union of cliques by making the fewest possible edits to the edges. We introduce a natural interpretation of this problem in temporal graphs, whose ...
Comments
Information & Contributors
Information
Published In
October 2024
5705 pages
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2024
Check for updates
Author Tags
Qualifiers
- Tutorial
Funding Sources
- DARPA
- NSF
- the Army Research Laboratory
Conference
CIKM '24
Sponsor:
CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management
October 21 - 25, 2024
ID, Boise, USA
Acceptance Rates
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 189Total Downloads
- Downloads (Last 12 months)189
- Downloads (Last 6 weeks)61
Reflects downloads up to 01 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in